Masked regularization in sparse autoencoders disrupts token co-occurrences to reduce feature absorption, enhance probing, and narrow OOD gaps across architectures and sparsity levels.
How llms learn: Tracing internal representations with sparse au- toencoders
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Language model features form an early stable carrier scaffold of about 50 sparse features that is load-bearing, predictable from onset firing, and recruits most later features.
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.
-
Features have life history. And we should care
Language model features form an early stable carrier scaffold of about 50 sparse features that is load-bearing, predictable from onset firing, and recruits most later features.