Mechanistic Interpretability Benchmark

university

https://mib-bench.github.io

AI & ML interests

Principled evaluation of mechanistic interpretability methods.

Recent Activity

sarahwie updated a dataset 3 days ago

mib-bench/ravel

sarahwie updated a dataset 4 days ago

mib-bench/arithmetic_subtraction

sarahwie updated a dataset 4 days ago

mib-bench/arithmetic_addition

View all activity

Collections 1

models 3

mib-bench/mib-causalvariable-example

Updated 5 days ago

mib-bench/interpbench

Updated 17 days ago

mib-bench/mib-circuits-example

datasets 7

mib-bench/ravel

Viewer • Updated 3 days ago • 117k • 60

mib-bench/arithmetic_subtraction

Viewer • Updated 4 days ago • 20.9k • 85

mib-bench/arithmetic_addition

Viewer • Updated 4 days ago • 40.4k • 94

mib-bench/ioi

Viewer • Updated 5 days ago • 21k • 329

mib-bench/arc_easy

Viewer • Updated Jan 25 • 4.01k • 26

mib-bench/arc_challenge

Viewer • Updated Jan 25 • 2k • 34

mib-bench/copycolors_mcqa

Viewer • Updated Jan 16 • 1.89k • 114