method
active
method:linear-decodingLinear Decoding
Correlative technique measuring the type of information encoded in distributed representations via linear predictability.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities 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
- Used to evaluate representation quality across VTAB tasks
- A resource-sensitive combinatory algebra with modalities for copying; provides a fine-grained model of computation.
- 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
- A straight vector in activation space, traditionally used for concept manipulation; claimed to be insufficient when true concept geometry is curved.