Mechanistic Interpretability Benchmark

AI & ML interests

Principled evaluation of mechanistic interpretability methods.

Recent Activity

amueller  updated a Space 4 days ago

mib-bench/leaderboard

amueller  updated a model 4 days ago

mib-bench/mib-circuits-example

amueller  updated a Space 6 days ago

mib-bench/leaderboard

View all activity

Team members 19