📝 SummarXiv

Abstract

We provide evidence that eigenanalysis of the empirical neural tangent kernel (eNTK) can surface the features used by trained neural networks. Across two standard toy models for mechanistic interpretability, Toy Models of Superposition (TMS) and a 1-layer MLP trained on modular addition, we find that the eNTK exhibits sharp spectral cliffs whose top eigenspaces align with ground-truth features. In TMS, the eNTK recovers the ground-truth features in both the sparse (high superposition) and dense regimes. In modular arithmetic, the eNTK can be used to recover Fourier feature families. Moreover, we provide evidence that a layerwise eNTK localizes features to specific layers and that the evolution of the eNTK eigenspectrum can be used to diagnose the grokking phase transition. These results suggest that eNTK analysis may provide a practical handle for feature discovery and for detecting phase changes in small models.