arxiv:2501.16496
Atticus Geiger
atticusg
AI & ML interests
NLP, explainable AI, causality
Recent Activity
authored
a paper
18 days ago
Open Problems in Mechanistic Interpretability
upvoted
a
paper
about 1 month ago
Enhancing Automated Interpretability with Output-Centric Feature
Descriptions
updated
a dataset
2 months ago
atticusg/ravel
Organizations
Papers
17
models
None public yet