Sparse encoding appears to stratify and compress feature representations, but the claimed causal link between cluster separation and reconstruction is not supported.
Towards monosemanticity: Decomposing language models with dictionary learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Sparsification and Reconstruction from the Perspective of Representation Geometry
Sparse encoding appears to stratify and compress feature representations, but the claimed causal link between cluster separation and reconstruction is not supported.