Sparse Auto-Encoders (SAEs) for Mechanistic Interpretability Collection A compilation of sparse auto-encoders trained on large language models. • 37 items • Updated 17 days ago • 18
Interpretability tools Collection Opening the hood of Computer Vision model for example ResNets, ConvNext & DETR, multimodal models and NLP models:BERT & GPTs. • 7 items • Updated 7 days ago • 2
Running 93 The Eiffel Tower Llama 📝 93 Explore the Eiffel Tower Llama experiment with open-source models
Speech Evals Collection Synthesized speech evals generated by MistralAI from popular text evaluation datasets to evaluate spoken-language reasoning capabilities of Audio LLMs • 3 items • Updated Nov 28, 2025 • 12
Transformer Explainer: Interactive Learning of Text-Generative Models Paper • 2408.04619 • Published Aug 8, 2024 • 174
Interpretability tools Collection Opening the hood of Computer Vision model for example ResNets, ConvNext & DETR, multimodal models and NLP models:BERT & GPTs. • 7 items • Updated 7 days ago • 2
Diffusion model tools Collection a couple of controlnets to improve various aspects of an images • 8 items • Updated 20 days ago
Datasets Collection Interesting datasets to help train LLMs and beyond • 45 items • Updated 21 days ago
Datasets Collection Interesting datasets to help train LLMs and beyond • 45 items • Updated 21 days ago