Toy Models of Superposition in Mechanistic Interpretability

Research question

Why are neurons polysemantic, and how do models represent more features than dimensions?

Key findings

Superposition arises when sparse features exceed dimensions; features form geometric structures - Motivates dictionary-learning approaches to recover features

Sources

arxiv.orghttps://arxiv.org/abs/2209.10652

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Submit research Report a correction or request removal

Related in Research Paper Library

X-SPUR: Explainable Surprisal-Based Protocol-Aware Unsupervised Reasoning for Automotive Ethernet Intrusion Detection

Automotive Ethernet carries heterogeneous multi-protocol traffic in modern in-vehicle networks, where labeled attack data are rarely available and the strongest prior unsupervised detector still relies on handcrafted…

Mechanistic interpretability2026

Delphi Scanner: efficient and interpretable static malware detection via API sequence modeling

Static malware detection for Windows Portable Executable files demands a careful balance between detection effectiveness, computational efficiency, and analytical interpretability. This paper introduces Delphi…

Mechanistic interpretability2026

Influence Score and Transformers interpretability: Measure of the Effective Impact of Attention Heads at inference time

We propose an influence score to quantify the contribution of attention heads to classification decisions in Transformer-based models designed for prompt injection detection. The score combines directional influence…

Mechanistic interpretability2026