Zou et al. 2023 - Representation Engineering: A Top-Down Approach to AI Transparency

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Representational Transparencyconcept0.782
  Property of conscious representations: they do not contain information about the fact that they are representations at the level of the representation itself
• Representation engineering for large-language models: Survey and research challenges (Bartoszcze et al., 2025)concept0.775
  Survey of representation engineering methods cited as related work
• Representation Engineeringframework0.768
  A class of methods that modify how models internally process representations; SOO fine-tuning fits within this framework
• Bai et al. 2022: Constitutional AI — harmlessness from AI feedbackconcept0.765
  Paper on AI-feedback fine-tuning as alternative to human-feedback RLHF; cited as ref 20
• Representation engineering successfully quantifies deception via high-accuracy steering vectors, establishing it as a measurable property of model representationsclaim0.762
  Key interpretive claim that deception has a tractable geometric signature in activation space
• Evans et al. 2021 - Truthful AI: Developing and Governing AI that Does Not Lieconcept0.754
  Reference establishing the truthfulness/honesty distinction and need for honest AI
• Representational abstraction of truth may emerge more clearly with model scaleclaim0.751
  Interpretation of weaker PCA separation and lower ASR in smaller models
• The only human oversight is provided through a list of rules or principles, and so we refer to the method as 'Constitutional AI'.quote0.746
  Defines the core concept of the paper.