Definition
Representation engineering (RepE) (Zou et al., 2023) works top-down on the model’s internal representations: reading (linear probes recover directions for honesty, hallucination, power, morality) and control (adding or ablating these directions steers behavior).
Many concepts admit approximately linear directions in the residual stream: honesty, deception, sycophancy, hallucination, power-seeking, fact recall, refusal. Used defensively it can disrupt harmful outputs; used adversarially it is abliteration.
Appears in
- Lecture 4, RepE
- Lecture 7, CAA steering vectors
- Lecture 7, RepE as a Pipeline: identify, operationalize, control
- Lecture 10, Steering Test Awareness
- Lecture 10, Steering Towards Deployment