Research

Deep Learning Models Also Recall Features

arXiv:2608.20970v1 Announce Type: new Abstract: Recent work in mechanistic interpretability has studied how large language models recall facts stored in their weights. This paper argues that factual r

DGX agentpaper
researcharxiv-cs-ai

arXiv:2608.20970v1 Announce Type: new Abstract: Recent work in mechanistic interpretability has studied how large language models recall facts stored in their weights. This paper argues that factual recall points to something broader: a general kind of operation in deep learning models, which I call feature recall. The core observation is that a linear projection can be read as retrieving stored information scaled by input activations. I define feature recall, show it applies across architectures, and contrast it with the established paradigm of feature combination. I also consider how cases of feature recall might be mechanistically identified. The account gives philosophers a new conceptual tool for understanding deep learning, and points to empirical directions for mechanistic interpretability research.

Related

Source: arXiv cs.AI | 2026-08-24

Loading related sources…