Pith. sign in

Compact proofs of model performance via mechanistic interpretability, 2024

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

2 Pith papers citing it

fields

cs.LG 2

years

2026 1 2025 1

verdicts

UNVERDICTED 2

representative citing papers

Interactions Between Crosscoder Features: A Compact Proofs Perspective

cs.LG · 2026-06-08 · unverdicted · novelty 6.0

Derives an interaction measure between crosscoder features from reconstruction error in compact proofs and applies it to produce computationally sparse crosscoders retaining 60% MLP performance with single-feature selection versus 10% for standard crosscoders.

Learning the symmetric group: large from small

cs.LG · 2025-02-18 · unverdicted · novelty 5.0

Transformer trained on S10 permutation prediction from transpositions generalizes to S25 with near 100% accuracy using identity augmentation and partitioned windows.

citing papers explorer

Showing 2 of 2 citing papers.

  • Interactions Between Crosscoder Features: A Compact Proofs Perspective cs.LG · 2026-06-08 · unverdicted · none · ref 19

    Derives an interaction measure between crosscoder features from reconstruction error in compact proofs and applies it to produce computationally sparse crosscoders retaining 60% MLP performance with single-feature selection versus 10% for standard crosscoders.

  • Learning the symmetric group: large from small cs.LG · 2025-02-18 · unverdicted · none · ref 10

    Transformer trained on S10 permutation prediction from transpositions generalizes to S25 with near 100% accuracy using identity augmentation and partitioned windows.