Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol

Summary

arXiv:2607.00089v1 Announce Type: new Abstract: Mechanistic interpretability has produced a rich inventory of component-level analyses that characterise what neural-network components encode and how they interact. Their outputs, however, are not easily reusable: selectivity tables, circuit diagrams, and feature lists remain locked in per-study notebooks - non-composable, not queryable in natural language, and not directly actionable for downstream audit or intervention. We study the representati

SpinGraph analysis pending — check back after processing.

• How to Allocate Your Tokens? Scaling Laws with Training Steps and Batch Size
• Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning
• Token Geometry
• Geometry-Aware R-Structured Kolmogorov-Arnold Networks
• On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain
• Conditional Inference Trees and Forests for Feature Selection