The field of interpretability has focused mainly on understanding model activations, not the computations themselves

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

• Activation-based interpretability does not immediately explain the computations that gave rise to activations; understanding parameters is necessary for deeper insightclaim0.854
  Motivates shift from studying model activations ('thoughts') to understanding parameters ('the computations themselves').
• Interpretability today is a pre-paradigmatic field lacking consensus on objects of study, methods, and evaluative standards.claim0.797
  Diagnosis of the state of the interpretability field, drawing on Kuhn's framework
• Bottom-up interpretability explains computation in the model's own terms rather than imposing top-down abstractionsclaim0.793
  VPD is positioned as advancing a paradigm shift from top-down mechanistic interpretability (activation-based) to parameter-centric, data-driven discovery.
• DAS's access to model outputs during training is responsible for much of its advantage over other interpretability methodsclaim0.793
  Author interpretation of selectivity results showing DAS advantage diminishes when controlling for expressivity
• How can mechanistic interpretability methods automatically identify attention computations that span multiple attention heads?question0.793
  Long-standing bottleneck in mechanistic interpretability that VPD addresses by working natively on attention weight matrices.
• Interpretability features converge across different model architectures, revealing structural similarities.claim0.791
• Causal abstraction is not enough for mechanistic interpretability because it becomes vacuous without assumptions about how models encode informationclaim0.779
  Central thesis of the paper
• Interpretability as technical grounding: activation patching and mechanism-finding validate the reflective/care/aliveness concepts.claim0.778