Representational Disentanglement

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

• Disentangled Representationsframework0.870
  Adjacent ML literature on separating independent factors of variation; related to but distinct from the polysemanticity problem studied here
• Disentanglementframework0.853
  Related research agenda seeking representations that separate conceptually distinct factors; contrasted with superposition approach
• Representational Divergenceconcept0.794
  Core phenomenon studied: when causal interventions shift internal representations away from the natural distribution
• Structure in representationsconcept0.786
  The central question of whether representational geometry implies corresponding computational structure
• Representational dynamicsconcept0.784
  The evolution of an agent's latent representations over the course of training, shown to align with reward improvement when causal emergence is high.
• Representation Designconcept0.782
  The aspect of design dealing with data structures, modules, and implementation.
• Distributed representationconcept0.779
  Idea that information is spread across many neurons; superposition is a subtype.
• Representational Isomorphismconcept0.777
  The desired property of a bidirectional, behavior-preserving mapping between model representations; the goal MAS pursues.