question
active
question:how-many-features-should-we-expect-to-be-stored-in-superposition

How many features should we expect to be stored in superposition?

Open question.

Source paper

extracted_from
Toy Models of Superposition
(2022) ·

Neighborhood — ranked by edge-count

Papers (1)

paper

Frameworks (1)

framework
  • Mathematical framework enabling recovery of high-dimensional sparse vectors from low-dimensional projections; theoretically underpins sparse autoencoder approach

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.