method
active
method:olah-et-al-computer-vision-model-analysisOlah et al. Computer Vision Model Analysis
2020 analysis of automatically trained computer vision models for functional structure; yielded Universality Hypothesis
Neighborhood — ranked by edge-count
Thinkers (1)
thinker
- Chris Olahintroduces
Findings (1)
finding
- Empirical finding supporting the Universality Hypothesis; extended by the paper to consciousness
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.
- Paper describing Llama 3 model family used in this study
- The computational approach used to simulate morphogenesis with cells as agents on a 2D grid; allows quantitative testing of stress-sharing hypothesis.
- Core cross-modal empirical result: larger and better language models align better with vision models
- Downstream task validating NLA utility for model auditing; agents succeed without access to misalignment training data.
- Neuroscientific model suggesting empathy is mediated by partial convergence of self and other representations
- Claims that alignment score is a proxy for general capability
- Success in cognitive science motivates the approach.
- Key cross-modal alignment result