concept
active
concept:knowledge-localizationKnowledge Localization
Technique for identifying where specific knowledge is stored in neural network layers via interventions
Neighborhood — ranked by edge-count
Papers (1)
paper
Thinkers (1)
thinker
- Kevin MengstudiesAuthor of ROME paper on locating and editing factual associations in GPT.
Concepts (1)
concept
- Neural Network Interpretabilityassociated_withThe field aimed at understanding what neural networks have learned; characterized as pre-paradigmatic in this paper
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.
- Chinn et al. showed that tactile target experience promotes earlier mirror self-recognition in infants; noted as a future extension
- Novel task asking which of 10 sentences received injection, cycling injection through all positions to average out positional bias
- The translation of semantic values into spatial coordinates and relations.
- Ability to apply learned solutions to novel circumstances.
- The ability to generalize across tasks; lacking in latent methods.
- Inference of parameters encoding contingencies of the world (e.g., likelihood matrix A) at slower timescale than perception.
- Ability to respond appropriately to novel situations based on past regularities; fundamental to learning and intelligence.
- Waddington's concept: developmental buffering that produces a stable phenotype despite genetic/environmental perturbation.