pith. sign in

ICLR , year=

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1 method 1

citation-polarity summary

fields

cs.LG 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

WriteSAE: Sparse Autoencoders for Recurrent State

cs.LG · 2026-05-12 · unverdicted · novelty 8.0 · 2 refs

WriteSAE introduces sparse autoencoders with rank-1 matrix atoms for recurrent state updates, allowing replacement tests that outperform deletion on 92.4% of positions and a formula predicting logit changes with R²=0.98.

citing papers explorer

Showing 2 of 2 citing papers.

  • WriteSAE: Sparse Autoencoders for Recurrent State cs.LG · 2026-05-12 · unverdicted · none · ref 90 · 2 links

    WriteSAE introduces sparse autoencoders with rank-1 matrix atoms for recurrent state updates, allowing replacement tests that outperform deletion on 92.4% of positions and a formula predicting logit changes with R²=0.98.

  • Convergent Stochastic Training of Attention and Understanding LoRA cs.LG · 2026-05-08 · unverdicted · none · ref 7

    Attention and LoRA regression losses induce Poincaré inequalities under mild regularization, so SGD-mimicking SDEs converge to minimizers with no assumptions on data or model size.