Mechanistic Interpretability Benchmark

AI & ML interests

Principled evaluation of mechanistic interpretability methods.

Recent Activity

yiksiu  updated a dataset 15 days ago

mech-interp-bench/arithmetic_division_private_test

yiksiu  published a dataset 15 days ago

mech-interp-bench/arithmetic_division_private_test

yiksiu  updated a dataset 15 days ago

mech-interp-bench/arithmetic_multiplication_private_test

View all activity

Team members 17