What is the connection between information encoding assumptions and causal abstraction?

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

• Causal abstraction implicitly relies on strong assumptions about feature encoding in DNNs, and becomes trivial without such assumptionsclaim0.840
  Authors' interpretation connecting their proof to practical interpretability methodology
• What can causal abstraction analyses tell us about how DNNs encode features if the methods themselves rely on encoding assumptions?question0.831
  Circular dependency problem raised in discussion
• Causal abstraction is not enough for mechanistic interpretability because it becomes vacuous without assumptions about how models encode informationclaim0.816
  Central thesis of the paper
• causal abstraction implicitly relies on strong assumptions about how features are encoded in deep neural networks (DNNs), and becomes trivial without such assumptionsquote0.804
  Load-bearing formulation of the paper's central argument
• Approximate Causal Abstractionconcept0.791
  Graded notion of causal abstraction measured by IIA; when IIA is alpha < 100%, the model is alpha-on-average approximately abstract.
• An interplay between causal abstraction and feature geometry deepens mechanistic understanding of language modelsclaim0.785
  Methodological claim about the scientific value of combining causal abstraction with representational geometry analysis
• 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 hypothesisclaim0.783
  Historical framing of how representation assumptions have evolved in causal interpretability
• Causal abstractionconcept0.779
  A framework the paper uses alongside feature geometry to deepen mechanistic understanding of LMs