Masked regularization in sparse autoencoders disrupts token co-occurrences to reduce feature absorption, enhance probing, and narrow OOD gaps across architectures and sparsity levels.
We conduct all experiments on Pythia-160M-deduped [17] and Gemma-2-2B [18]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Improving Robustness In Sparse Autoencoders via Masked Regularization
Masked regularization in sparse autoencoders disrupts token co-occurrences to reduce feature absorption, enhance probing, and narrow OOD gaps across architectures and sparsity levels.