Year: 2026
Type: preprint
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.
Source: arXiv (Cornell University)
Author: Beckmann, Pierre
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7204128190