pith. sign in

Towards monosemanticity: Decomposing language models with dictionary learning, 2023

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

2 Pith papers citing it

fields

cs.CV 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Markovian Circuit Tracing for Transformer State Dynamic

cs.LG · 2026-05-20 · unverdicted · novelty 7.0

This paper presents Markovian Circuit Tracing (MCT) as a benchmark and pipeline to extract and test state-transition structures in transformer activations using synthetic HMM tasks, demonstrating that state patching improves counterfactual predictions.

citing papers explorer

Showing 2 of 2 citing papers.

  • Markovian Circuit Tracing for Transformer State Dynamic cs.LG · 2026-05-20 · unverdicted · none · ref 30

    This paper presents Markovian Circuit Tracing (MCT) as a benchmark and pipeline to extract and test state-transition structures in transformer activations using synthetic HMM tasks, demonstrating that state patching improves counterfactual predictions.

  • SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery cs.CV · 2026-03-19 · unverdicted · none · ref 38

    SwiftGS uses episodic meta-training to predict geometry-radiation-decoupled Gaussian primitives and a lightweight SDF for zero-shot 3D satellite surface reconstruction with physics-aware rendering.