conftrace_

modular addition

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

fourier feature (2) mechanistic interpretability (2) algebraic task (1) overfitting (1) grokking (1) quadratic networks (1) mechanistic explanation (1) mlp layer (1) neural network representation (1) kernel regime (1)

Papers

Feature emergence via margin maximization: case studies in algebraic tasks ICLR 2024 Pre-trained Large Language Models Use Fourier Features to Compute Addition NeurIPS 2024 Why Do You Grok? A Theoretical Analysis on Grokking Modular Addition ICML 2024 The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks NeurIPS 2023