concept
active
concept:streetlight-interpretabilityStreetlight interpretability
Studying tasks chosen only because simple to define.
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Lists issues: concept-based tasks, flawed decomposition, low faithfulness.
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.
- The capability to explain model predictions; a central theme of the paper, with disruption profiles as vehicle.
- Socio-philosophical open question.
- Advantage of DiffLogic CA over NCA — learned rules are pure binary logic circuits that can be visualized and analyzed
- Cases where subspace interventions change model behaviour through parallel pathways rather than the target feature
- Proposed paradigm for evaluating interpretability work through empirical falsifiability rather than benchmarks or user studies
- Method using large language models (Claude) to generate and test explanations of features at scale
- An interpretability paradigm that explains computation in the model's own terms, rather than imposing top-down abstractions; VPD aims to realize this.
- Second approach: propose concepts and find components corresponding to them.