arxiv:2506.10920
Or Shafran
ordavids1
AI & ML interests
None yet
Recent Activity
upvoted
a
collection
1 day ago
🔍 Interpretability & Analysis of LMs
commented on
a paper
about 2 months ago
Decomposing MLP Activations into Interpretable Features via
Semi-Nonnegative Matrix Factorization
authored
a paper
about 2 months ago
Decomposing MLP Activations into Interpretable Features via
Semi-Nonnegative Matrix Factorization
Organizations
None yet