Mechanistic Interpretability Benchmark

AI & ML interests

Principled evaluation of mechanistic interpretability methods.

Recent Activity

hadasor  submitted a paper about 2 months ago

Large Language Models Generate Harmful Content Using a Distinct, Unified Mechanism

nepp1d0  authored a paper 2 months ago

InTraVisTo: Inside Transformer Visualisation Tool

amueller  updated a Space 3 months ago

mib-bench/leaderboard

View all activity

Team members 20