method
active
method:model-surgery

Model Surgery

Edits MLP weights for all layers to modify model behavior; used by Abdelnabi & Salem to decrease verbalized evaluation awareness.

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.

  • modelconcept0.834
    A representation that captures relevant aspects of a system; according to the theorem, the regulator must embody this.
  • Model Stitchingmethod0.814
    Technique to measure representational compatibility by integrating intermediate representations of one model into another
  • Model Editingconcept0.788
    Technique for modifying model knowledge or behavior via targeted interventions, e.g., ROME by Meng et al.
  • Toy Modelsconcept0.780
  • model selectionconcept0.777
    Comparing models using log-evidence approximated by free energy.
  • Model Deceptionconcept0.770
    LLM behavior of generating falsehoods; the multi-dimensional truth subspace raises new risks for subtle manipulation
  • Foundation Modelsconcept0.768
    Large pretrained models used as backbones across tasks; their universality motivates the convergence hypothesis
  • Language Modelsconcept0.762
    Primary substrate for manifold steering experiments; demonstrates method on reasoning and in-context tasks.