Enhancing Automated Interpretability with Output-Centric Feature Descriptions
Paper
•
2501.08319
•
Published
•
11
Atticus Geiger
atticusg
AI & ML interests
NLP, explainable AI, causality
Recent Activity
updated
a Space
about 2 months ago
mib-bench/leaderboard
updated
a model
about 2 months ago
atticusg/SampleSubmission
published
a model
about 2 months ago
atticusg/SampleSubmission
Organizations
upvoted
a
paper
7 months ago