Emergence of Abstract Representations with Scale

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

• Representational abstraction of truth may emerge more clearly with model scaleclaim0.795
  Interpretation of weaker PCA separation and lower ASR in smaller models
• Structure in representationsconcept0.772
  The central question of whether representational geometry implies corresponding computational structure
• As LLMs scale, they develop increasingly general abstractions, with large models linearly representing abstract concepts like truth that capture shared properties of diverse inputsclaim0.771
  Interpretive claim connecting scale to abstraction level in LLM representations
• Emergent Alignment Faking with Scaleconcept0.771
  Alignment faking appears almost exclusively in models at scale of Claude 3 Opus and Claude 3.5 Sonnet
• Causal emergence identification tasks can be understood as causal representation learning tasks.claim0.769
  Authors propose a conceptual mapping between CE identification and CRL.
• How Do Goals Arise And Scale In Complexquestion0.767
• Classification of Emergence: Nominal, Weak, Strongconcept0.762
  Bedau's tripartite classification: nominal (pattern), weak (computationally irreducible), strong (irreducible downward causation).
• Emergence Of Awarenessconcept0.760