Strong τ-Abstraction

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• well-known key τ for type/classconcept0.761
  A distinguished key used in α1 to identify an object's type as the starting point for lookup.
• What standard abstraction to use for (⊸)?question0.740
  Question prompting the use of Category for linear transformations.
• dynamic binding for class-based inheritance using σ and τconcept0.738
  Combining α1 with τ (type) and β1 with σ (supertype) to model class-based OO with inheritance in the associative model.
• Causal abstractionconcept0.732
  A framework the paper uses alongside feature geometry to deepen mechanistic understanding of LMs
• interpretive abstraction (method)method0.726
  Programming technique to restructure a fine-grained Linda program for efficiency by replacing live data structures with passive ones and coarser-grain processes.
• Representational Transparencyconcept0.726
  Property of conscious representations: they do not contain information about the fact that they are representations at the level of the representation itself
• Representational abstraction of truth may emerge more clearly with model scaleclaim0.720
  Interpretation of weaker PCA separation and lower ASR in smaller models
• Latent Variables in Distributed Abstractionconcept0.719
  Output of alignment map ϕ applied to DNN hidden states; basis for distributed causal abstraction