Nested 'Matryoshka' sparse autoencoders outperform pruned vanilla sparse autoencoders on reconstruction and recaptured language-model loss, but pruned vanilla features remain more interpretable.
pub/2022/toy_model/index.html
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Empirical Evaluation of Progressive Coding for Sparse Autoencoders
Nested 'Matryoshka' sparse autoencoders outperform pruned vanilla sparse autoencoders on reconstruction and recaptured language-model loss, but pruned vanilla features remain more interpretable.