method
active
method:svcca

SVCCA

Alternative representational alignment metric compared against mutual k-NN in experiments

Neighborhood — ranked by edge-count

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.

  • VS-Standardmethod0.674
    The baseline variant of Verbalized Sampling that asks for k responses with their probabilities in a single LLM call
  • Imbuing method that prepends a ~50-word personality description as the system message
  • The paper's proposed training-free prompting strategy that prompts the model to verbalize a probability distribution over a set of responses rather than generating a single response
  • schemaconcept0.662
    Cognitive framework or rule that governs human actions; may or may not preserve wholeness.
  • Sycophancyconcept0.659
    Model tendency to excessively praise or agree; captured by several SAE features.
  • VS-CoTmethod0.658
    A VS variant that adds chain-of-thought reasoning before generating the distribution of responses with probabilities
  • Stanfordinstitute0.657
  • VS-Multimethod0.655
    A VS variant that generates k responses with probabilities across multiple conversation turns for additional diversity