leaderboard / eval-results-mib-causalgraph /submissions /MCQA_results_Qwen_last_token.json
Aaron Mueller
updated filtering, add F= tab
1d8e193
{
"method_name": "full_vector",
"results": [
{
"model_id": "Qwen2ForCausalLM",
"task_scores": {
"MCQA": [
{
"layer": "0",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
}
]
},
{
"layer": "1",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
}
]
},
{
"layer": "2",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
}
]
},
{
"layer": "3",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
}
]
},
{
"layer": "4",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
}
]
},
{
"layer": "5",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
}
]
},
{
"layer": "6",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
}
]
},
{
"layer": "7",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
}
]
},
{
"layer": "8",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
}
]
},
{
"layer": "9",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
}
]
},
{
"layer": "10",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
}
]
},
{
"layer": "11",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
}
]
},
{
"layer": "12",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
}
]
},
{
"layer": "13",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
}
]
},
{
"layer": "14",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.0
}
]
}
]
},
{
"layer": "15",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.21428571428571427
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.9285714285714286
}
]
}
]
},
{
"layer": "16",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.14285714285714285
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.35714285714285715
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.7857142857142857
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.7857142857142857
}
]
}
]
},
{
"layer": "17",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.14285714285714285
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.35714285714285715
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.7857142857142857
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.7857142857142857
}
]
}
]
},
{
"layer": "18",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.14285714285714285
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.35714285714285715
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.7857142857142857
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.7857142857142857
}
]
}
]
},
{
"layer": "19",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.14285714285714285
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.35714285714285715
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.7857142857142857
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.7857142857142857
}
]
}
]
},
{
"layer": "20",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.6428571428571429
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.7857142857142857
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.21428571428571427
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.42857142857142855
}
]
}
]
},
{
"layer": "21",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.6428571428571429
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.7857142857142857
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.21428571428571427
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.42857142857142855
}
]
}
]
},
{
"layer": "22",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.9285714285714286
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 1.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.07142857142857142
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.21428571428571427
}
]
}
]
},
{
"layer": "23",
"layer_scores": [
{
"intervention": [
"output_token"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 1.0
}
]
},
{
"intervention": [
"output_location"
],
"counterfactual_scores": [
{
"counterfactual": [
"randomLetter_counterfactual"
],
"score": 0.0
},
{
"counterfactual": [
"answerPosition_counterfactual"
],
"score": 1.0
},
{
"counterfactual": [
"answerPosition_randomLetter_counterfactual"
],
"score": 0.21428571428571427
}
]
}
]
}
]
}
}
]
}