method
active
method:single-prompt-concept-vector-extraction

Single-prompt concept vector extraction

Method using activations from the prompt 'Tell me about {word}' minus mean over other random words to obtain concept vectors.

Neighborhood — ranked by edge-count

Methods (1)

method
  • Causal intervention technique: edit NLA explanation, reconstruct via AR, use difference as steering vector to manipulate model behavior.

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.

  • Method for obtaining concept vectors by subtracting activations from two contrasting prompts.
  • concept vectorconcept0.790
    Computed directional vector in activation space representing a specific concept, used for injection experiments
  • Procedure extracting concept vectors as difference of mean activations between concept-exemplifying and baseline/negative sentences
  • Pipeline for extracting mean post-MLP residual stream activations from model responses under persona-specific system prompts to produce role vectors
  • How a neural network encodes a semantic concept internally, argued to be better captured by manifolds than by atomic features.
  • Sense Vectorsconcept0.701
    Vectors acquired during pretraining in Backpack LMs that have a multiplication effect on model generation
  • Concept Algebraframework0.700
    Probabilistic framework formalizing concept-specific subspaces for targeted steering in generative models.
  • Models maintain ability to accurately transcribe input text while simultaneously reporting on injected thoughts, all models perform above chance, Opus 4/4.1 best.