Mor Geva's picture

1 2

Mor Geva

mega

·

https://mega002.github.io/

AI & ML interests

None yet

Recent Activity

authored a paper 2 days ago

Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization

authored a paper 5 months ago

Open Problems in Mechanistic Interpretability

authored a paper 5 months ago

Enhancing Automated Interpretability with Output-Centric Feature Descriptions

View all activity

Organizations

Papers 12

arxiv:2506.10920

arxiv:2501.16496

arxiv:2501.08319

arxiv:2408.03325

models 0

None public yet

datasets 0

None public yet