framework
active
framework:biology-analogy-for-interpretabilityBiology analogy for interpretability
Frames model interpretability like biology, features as cells, tools as microscopes.
Neighborhood — ranked by edge-count
Papers (1)
paper
- On the Biology of a Large Language Modelintroducesmentions
Concepts (1)
concept
- FeaturesextendsInterpretable concept representations hypothesized as basic units of computation.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Proposed paradigm for evaluating interpretability work through empirical falsifiability rather than benchmarks or user studies
- The capability to explain model predictions; a central theme of the paper, with disruption profiles as vehicle.
- Proposal for standard studied networks akin to Drosophila.
- Cases where subspace interventions change model behaviour through parallel pathways rather than the target feature
- The field aimed at understanding what neural networks have learned; characterized as pre-paradigmatic in this paper
- Forward-looking suggestion for how inner interpretability could extend the indicator method
- Explaining activations without understanding mechanism.
- Socio-philosophical open question.