Privileged Bases Hypothesis

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

• Privileged Basisconcept0.823
  A property of activations where neural network features align with basis dimensions due to sparse activation functions; absent in the residual stream but present in tokens, attention patterns, and MLP activations
• Early causal abstraction methods (Geiger et al. 2021) implicitly rely on the privileged bases hypothesis, while recent methods (Geiger et al. 2024b) rely on the linear representation hypothesisclaim0.766
  Historical framing of how representation assumptions have evolved in causal interpretability
• Genesis Hypothesisframework0.750
  The conjecture that consciousness does not result from the organized mind but creates and maintains complex models of reality; forms at the beginning of mental development
• Reward Hypothesisconcept0.748
  The claim in RL that any goal can be expressed as maximizing the expected cumulative sum of a scalar reward signal.
• Capacity Hypothesishypothesis0.739
  Bigger models are more likely to converge to a shared representation than smaller models because they can better approximate the global optimum
• Privileged self-accessconcept0.731
  Models predict their own hypothetical behavior better than other models can, demonstrating a form of privileged self-access per Binder et al. 2024
• Superposition Hypothesisframework0.731
  Core theoretical framework: neural networks represent more features than neurons by encoding features as directions in superposition
• No Privileged Material Substrate for Mindclaim0.729
  Minds not exclusively neural; basal cognition identifies intelligences in single cells, plants, tissues, swarms; brains pre-date neurons evolutionarily.