method
active
method:head-loadings

Head Loadings

Per-edge contribution of each attention head to attribution graph edges.

Neighborhood — ranked by edge-count

Methods (2)

method

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.

  • Dynamic Loadingmethod0.724
    Modules loaded on demand at command invocation or through programmed calls; no separate linker; each module present once in memory.
  • Quadratic scaling.
  • Workspace loadingconcept0.698
    Cosine similarity of a concept's lens vector with the residual stream; predicts swap success.
  • The pass rate among a model's skill-loaded trajectories, measuring outcome conditioned on harness activation
  • Capability to load application classes at runtime via late binding, enabling piecemeal addition of features without recompilation.
  • Boundary headsconcept0.684
    Attention heads whose QK twists count manifolds to detect approaching line end.
  • Attention headsconcept0.683
    Transformer attention heads that could be recruited to extract different kinds of information (text vs. thoughts).
  • Skill-Load Rateconcept0.679
    The fraction of trajectories in which an agent actively loads at least one skill into its context