AINeutralarXiv – CS AI · Mar 117/10
🧠
From Data Statistics to Feature Geometry: How Correlations Shape Superposition
Researchers introduce Bag-of-Words Superposition (BOWS) to study how neural networks arrange features in superposition when using realistic correlated data. The study reveals that interference between features can be constructive rather than just noise, leading to semantic clusters and cyclical structures observed in language models.