pith. sign in

An R2 near 1 at n=k i indicates compact subspace capture

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

Do Sparse Autoencoders Capture Concept Manifolds?

cs.LG · 2026-04-30 · unverdicted · novelty 6.0

Sparse autoencoders capture concept manifolds globally via compact feature groups or locally via selective tiling but typically recover them suboptimally in a fragmented dilution regime.

citing papers explorer

Showing 1 of 1 citing paper.

  • Do Sparse Autoencoders Capture Concept Manifolds? cs.LG · 2026-04-30 · unverdicted · none · ref 10

    Sparse autoencoders capture concept manifolds globally via compact feature groups or locally via selective tiling but typically recover them suboptimally in a fragmented dilution regime.