question

active

question:is-the-apparent-universality-of-some-low-level-vision-features-the-exception-or-the-rule

Is 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

Zoom In: An Introduction to Circuits

(2020) · Chris Olah · Nick Cammarata · Ludwig Schubert · Gabriel Goh +2

Neighborhood — ranked by edge-count

Claims (1)

claim

Analogous features and circuits form across models and tasks.
gates
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 edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Feature Universalityconcept0.764
Property of features that form consistently across different models trained on the same or similar data, suggesting features are real representational units
"[W]e must confess that perception, and what depends upon it, is inexplicable in terms of mechanical reasons... when inspecting its interior, we will find only parts that push one another, and we will never find anything to explain a perception."quote0.749
Canonical illustration of the Hard Problem intuition that any functional/mechanical explanation faces an explanatory gap for perception
The rule of hierarchy of color areas is almost universally followed in things with inner light; equal areas of several colors almost never occur in such works.claim0.748
Feature universality across independently trained models suggests features have some existence beyond individual modelsclaim0.748
Authors take agnostic position on ontological status but universality evidence pushes toward features being real
We hypothesize that high-low frequency detectors, if predicted by artificial neural network universality, might be found in biological neural networks.hypothesis0.748
Specific cross-domain prediction mentioned by neuroscientists in conversation with the authors
"[W]e must confess that perception, and what depends upon it, is inexplicable in terms of mechanical reasons... we will find only parts that push one another, and we will never find anything to explain a perception."quote0.744
Load-bearing quote from Monadology §17 providing earliest clear statement of the Hard Problem
Producing the exact shape from personal vision brings the thing to lifeclaim0.737
The styrofoam method allows the exact shape felt right to be produced, and that personal exactness yields spiritual quality.
Automated interpretability using LLMs can usefully score feature specificity.claim0.736
Claude 3 Opus ratings aligned with human judgment of feature descriptions.