pith. sign in

We consider a feature that represents a first-letter concept as having F1 >0.4 on the task

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.

  • Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders cs.LG · 2026-05-08 · unverdicted · none · ref 29 · 2 links

    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.