Many distinct SAE features share identical explanations, with the average annotation resolving only 70% of feature identity in a large annotated dataset.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.LG 3years
2026 3roles
baseline 1polarities
baseline 1representative citing papers
Compositional interpretability defines explanations as commuting syntactic-semantic mapping pairs grounded in compositionality and minimum description length, with compressive refinement and a parsimony theorem guaranteeing concise human-aligned decompositions.
Tree SAE learns hierarchical feature structures by combining activation coverage with a new reconstruction condition, outperforming prior SAEs on hierarchical pair detection while matching state-of-the-art benchmark performance.
citing papers explorer
-
Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features
Many distinct SAE features share identical explanations, with the average annotation resolving only 70% of feature identity in a large annotated dataset.
-
From Mechanistic to Compositional Interpretability
Compositional interpretability defines explanations as commuting syntactic-semantic mapping pairs grounded in compositionality and minimum description length, with compressive refinement and a parsimony theorem guaranteeing concise human-aligned decompositions.
-
Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders
Tree SAE learns hierarchical feature structures by combining activation coverage with a new reconstruction condition, outperforming prior SAEs on hierarchical pair detection while matching state-of-the-art benchmark performance.