question
active
question:is-the-apparent-universality-of-some-low-level-vision-features-the-exception-or-the-ruleIs the apparent universality of some low-level vision features the exception or the rule?
Open empirical question following anecdotal cross-model universality findings
Source paper
extracted_from(2020) · Chris Olah · Nick Cammarata · Ludwig Schubert · Gabriel Goh +2
Neighborhood — ranked by edge-count
Claims (1)
claim
- Third of three speculative claims asserting that learned features are not model-specific but represent universal solutions to learning problems
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.
- Third empirical pattern.
- Property of features that form consistently across different models trained on the same or similar data, suggesting features are real representational units
- Low-cosine shared features are best interpreted as same features used differently in the two modelsclaim0.761Interpretation of cosine distribution.
- Some features are easy to intervene on while very similar-looking ones have little or no effectfinding0.757Observation from intervention phenomenology.
- Main proposal.
- Future-work perspective.
- Canonical illustration of the Hard Problem intuition that any functional/mechanical explanation faces an explanatory gap for perception