Mechanistic Interpretability Benchmark

university

https://mib-bench.github.io

AI & ML interests

Principled evaluation of mechanistic interpretability methods.

Recent Activity

shunshao updated a Space 15 days ago

mib-bench/leaderboard

atticusg updated a Space 16 days ago

mib-bench/leaderboard

atticusg updated a Space 16 days ago

mib-bench/leaderboard

View all activity

mib-bench 's models 3

mib-bench/mib-causalvariable-example

mib-bench/interpbench

mib-bench/mib-circuits-example