method
active
method:linear-decoding

Linear Decoding

Correlative technique measuring the type of information encoded in distributed representations via linear predictability.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • The idea that features are encoded as directions in activation space.
  • The established finding that transformer LLMs encode many interpretable concepts as linear directions in activation space
  • Linear Probingmethod0.786
    Used to evaluate representation quality across VTAB tasks
  • Neural Decodingframework0.782
  • A resource-sensitive combinatory algebra with modalities for copying; provides a fine-grained model of computation.
  • linearityconcept0.778
    The sequential, continuous order of text, often challenged by diagrammatic branching.
  • IID mass-mean probing coincides with LDA when covariance is known; used to derive the corrected probe formula
  • linear directionconcept0.776
    A straight vector in activation space, traditionally used for concept manipulation; claimed to be insufficient when true concept geometry is curved.