The spectral edge transitions from a gradient-driven functional direction before grokking to a perturbation-flat, ablation-critical compression axis at grokking, forming three universality classes predicted by a gap flow equation.
Progress measures for grokking via mechanistic interpretability
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Lifecycle of the Spectral Edge: From Gradient Learning to Weight-Decay Compression
The spectral edge transitions from a gradient-driven functional direction before grokking to a perturbation-flat, ablation-critical compression axis at grokking, forming three universality classes predicted by a gap flow equation.