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

paper

method

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

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.

Contrastive concept vector extractionmethod0.829
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
concept vector computationmethod0.771
Procedure extracting concept vectors as difference of mean activations between concept-exemplifying and baseline/negative sentences
Persona vector extraction via contrastive activationmethod0.743
Method of extracting persona vectors by contrasting activations when model is prompted to exhibit vs suppress a trait
Contrastive Persona Vector Extraction Protocolmethod0.727
Named procedure for extracting persona vectors from mean residual-stream activation differences between trait-expressing and non-expressing responses
Automated Persona Vector Extraction Pipelinemethod0.726
The paper's core automated pipeline that takes a trait name and description as input and outputs a corresponding persona vector via contrastive prompting
Role Vector Extractionmethod0.726
Pipeline for extracting mean post-MLP residual stream activations from model responses under persona-specific system prompts to produce role vectors
Persona Vector Extraction via Difference-of-Meansmethod0.722
Core method for extracting persona vectors by contrasting mean activations under persona-eliciting vs. suppressing prompts