concept
active
concept:steering-entanglementSteering Entanglement
Steering one concept shifts beliefs in related unintended concepts.
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- Model Self-Repairassociated_withLater layers correct single-layer steering interventions.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Less hierarchical than embedment; multiple texts work into and out of each other, creating associations across levels and connecting any single text to the matrix of all others.
- A method for modifying model behavior by adding perturbation vectors to activations, used here to try to reduce eval awareness.
- Ability to steer model behavior in two opposite semantic directions on a trait.
- Using interventions to guide model generation behavior, e.g., adding sentiment vectors at inference time
- Steering variant that rotates hidden states toward a target feature vector, addressing how to steer
- Parent concept; the practice of controlling neural network outputs by manipulating internal representations.
- The central phenomenon introduced by this paper: inference-time recovery from irrelevant activation steering in LLMs
- Novel method that applies intervention only when the model begins a new thinking step (at the \n\n delimiter) rather than at every token