method
active
method:local-replacement-model

Local replacement model

CLT plus error nodes and original attention patterns, local to a prompt.

Neighborhood — ranked by edge-count

Frameworks (1)

framework

Concepts (1)

concept
  • Uninterpretable nodes representing replacement model reconstruction error.

Methods (1)

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.

  • Substitutes all MLP outputs with CLT reconstructions.
  • Model changeconcept0.718
    When a single conversation involves different models, e.g., routing between standard and reasoning models
  • modelconcept0.717
    A representation that captures relevant aspects of a system; according to the theorem, the regulator must embody this.
  • Language Modelconcept0.712
    Primary test domain for manifold steering, including reasoning and ICL tasks
  • Model Self-Repairconcept0.709
    Later layers correct single-layer steering interventions.
  • Foundation Modelsconcept0.704
    Large pretrained models used as backbones across tasks; their universality motivates the convergence hypothesis
  • model selectionconcept0.703
    Comparing models using log-evidence approximated by free energy.
  • Preference Modelframework0.702
    A model trained on comparison data to assign scores to responses, used as reward signal in RLHF/RLAIF.