paper
referenced-only
paper:sparse-crosscoders-994b59

Sparse Crosscoders for Cross-Layer Features and Model Diffing

Methods (13)

Frameworks (3)

  • Crosscoders
    Learn a shared feature space across two models; basis of the work.
  • Sparse Autoencoder
    Interpretability framework used to decompose layer-40 activations into sparse feature sets for studying emotional alignment and persistence
  • Superposition Hypothesis
    Core theoretical framework: neural networks represent more features than neurons by encoding features as directions in superposition

Datasets (2)

Findings (17)

Claims (13)

Related work— refs + corpus + external arXiv

Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.

Similar preprints — Semantic Scholar

Cited by (5)