claim
active
claim:neural-networks-represent-features-as-directions-in-activation-space

Neural networks represent features as directions in activation space

Linear representation hypothesis supported by empirical and theoretical arguments.

Source paper

extracted_from
Toy Models of Superposition
(2022) ·

Neighborhood — ranked by edge-count

Papers (1)

paper

Frameworks (1)

framework
  • The hypothesis that models internalize concepts as approximately linear directions in representation space; used to interpret MDS injection behavior

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.