Mechanistic Interpretability Benchmark

AI & ML interests

Principled evaluation of mechanistic interpretability methods.

Recent Activity

nepp1d0  authored a paper about 14 hours ago

InTraVisTo: Inside Transformer Visualisation Tool

amueller  updated a Space 23 days ago

mib-bench/leaderboard

hij  authored a paper 4 months ago

Blackbox Model Provenance via Palimpsestic Membership Inference

View all activity

Team members 20