concept
active
concept:scope-generalization

scope generalization

Generalization from 2-digit to 3-4 digit arithmetic; limited by mismatch dr.

Neighborhood — ranked by edge-count

Concepts (2)

concept
  • Generalisation
    related_to
    Ability to respond appropriately to novel situations based on past regularities; fundamental to learning and intelligence.
  • Generalization
    related_to
    Ability to apply learned solutions to novel circumstances.

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.

  • The ability to generalize across tasks; lacking in latent methods.
  • Abstracting from specific memories (e.g., specific leaves) to general lessons (food).
  • The ability of probes trained on one dataset to transfer accurately to topically and structurally different datasets
  • Measuring AUROC of a probe trained on one task when evaluated on another task to assess universality.
  • Ability to predict correctly for stimulus-action pairs never previously experienced by inferring structural rules; key measure for TEM-t performance.
  • Whether learned cones transfer effectively across model families (Qwen vs Gemma) and sizes
  • The capacity of a probe trained on one true/false dataset to accurately classify statements from topically and structurally different datasets
  • Models learning goals that generalize undesirably outside training distribution; alignment faking is a challenging instance