question
active
question:how-does-superposition-relate-to-non-robust-featuresHow does superposition relate to non-robust features?
Open question.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Toy Models of Superpositionmentions
Hypotheses (1)
hypothesis
- Open question linking to Goh.
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.
- Posed on SAE results.
- Open question.
- superposition is deeply linked to the ability to identify and enumerate over all features in a modelquote0.818Safety rationale.
- Core mechanism statement.
- Robustness influences superposition, predicting lower SAE loss in more robust models.hypothesis0.805Popperian credit for surprising prediction.
- Discussion implication.
- Confound addressed.
- Mechanistic finding by Bricken et al. 2023 about how LLMs store features; cited as operational justification for pattern-repository assumption