hypothesis
active
hypothesis:different-neural-networks-learn-similar-features-and-circuits-to-one-another

Different neural networks learn similar features and circuits to one another

Universality hypothesis to be tested across families.

Source paper

extracted_from
Open Problems in Mechanistic Interpretability
(2025) · Lee Sharkey · Bilal I. Chughtai · Joshua Batson · Jack W. Lindsey +25

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • The hypothesis that analogous features and circuits reliably form across different neural network models and tasks

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.