hypothesis
active
hypothesis:useful-non-robust-features-could-be-an-artifact-of-superposition

Useful non-robust features could be an artifact of superposition

Open question linking to Goh.

Source paper

extracted_from
Toy Models of Superposition
(2022) ·

Neighborhood — ranked by edge-count

Papers (1)

paper

Thinkers (1)

thinker
  • Reported multimodal neurons in vision models including region neurons and person detector neurons

Questions (1)

question

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.