Pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Teach Old SAEs New Domain Tricks with Boosting

cs.LG · 2025-07-17 · conditional · novelty 6.0

Training a small secondary sparse autoencoder on the reconstruction error of a pretrained SAE improves domain-specific reconstruction and language-model perplexity without hurting general performance.

citing papers explorer

Showing 1 of 1 citing paper.

  • Teach Old SAEs New Domain Tricks with Boosting cs.LG · 2025-07-17 · conditional · none · ref 12

    Training a small secondary sparse autoencoder on the reconstruction error of a pretrained SAE improves domain-specific reconstruction and language-model perplexity without hurting general performance.