arXiv (All)
open access
Latent Algorithmic Structure Precedes Grokking: A Mechanistic Study of ReLU MLPs on Modular Arithmetic
Grokking-the phenomenon where validation accuracy of neural networks on modular addition of two integers rises long after training data has been memorized-has been characterized in previous works as producing sinusoidal input weight distributions in transformers and multi-layer perceptrons (MLPs). W
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Recursive State Compression in Artificial Intelligence: A Structural Correspondence with the Paton Recursive Pressure Field Equation#72663
- Fast Stencil Computations on a Single Arbitrarily Moving Interval#1084791
- Fast Stencil Computations on a Single Arbitrarily Moving Interval#919353
- Identity-Conditioned Latent Consistency Distillation for Face Synthesis#819081
- Identity-Conditioned Latent Consistency Distillation for Face Synthesis#809089
Record · ID 1342432
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive