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.
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
years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Markovian Circuit Tracing for Transformer State Dynamic
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
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.