arxiv:2506.10920
Or Shafran
ordavids1
AI & ML interests
None yet
Recent Activity
commented on
a paper
3 days ago
Decomposing MLP Activations into Interpretable Features via
Semi-Nonnegative Matrix Factorization
authored
a paper
3 days ago
Decomposing MLP Activations into Interpretable Features via
Semi-Nonnegative Matrix Factorization
Organizations
None yet
Papers
1
models
0
None public yet
datasets
0
None public yet