concept
active
concept:interpretability-illusionInterpretability Illusion
Cases where subspace interventions change model behaviour through parallel pathways rather than the target feature
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- interpretabilityrelated_toThe capability to explain model predictions; a central theme of the paper, with disruption profiles as vehicle.
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
- Method using large language models (Claude) to generate and test explanations of features at scale
- Advantage of DiffLogic CA over NCA — learned rules are pure binary logic circuits that can be visualized and analyzed
- Ian Goodfellow quote used to illustrate the pre-paradigmatic state of interpretability research
- An interpretability paradigm that explains computation in the model's own terms, rather than imposing top-down abstractions; VPD aims to realize this.
- The field aimed at understanding what neural networks have learned; characterized as pre-paradigmatic in this paper
- CIMC's methodology for evaluating whether a built system is conscious: combining multiple forms of evidence including predicted functional organization and developmental trajectories
- As models grow larger, the latent space volume grows exponentially, making enumeration impossible without decomposition