Least-confidence active learning appeared to increase feature overlap (superposition) in ResNet18 on CIFAR-10 and Tiny ImageNet, contrary to the authors' expectation, though the evidence is indirect and statistically unverified.
A mathematical framework for transformer circuits
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Superposition through Active Learning lens
Least-confidence active learning appeared to increase feature overlap (superposition) in ResNet18 on CIFAR-10 and Tiny ImageNet, contrary to the authors' expectation, though the evidence is indirect and statistically unverified.