Abstract
In this paper, we use toy models — small ReLU networks trained on synthetic data with sparse input features — to investigate how and when models represent more features than they have dimensions. We call this phenomenon superposition. When features are sparse, superposition allows compression beyond what a linear model would do, at the cost of "interference" that requires nonlinear filtering.
Related content
Investigating unintended model actions in our evaluations and internal use
This report describes examples of unintended model actions we’ve observed during evaluations and internal use of Claude.
Read moreThe missing map of the sky
Brice Ménard, an astrophysicist at Johns Hopkins University and a researcher at Anthropic, explains how he worked with Claude Science to produce the first complete map of the sky in UV light.
Read moreLaunching an opt-in vulnerability-finding service for open-source software
We’re making available OSS Scanner, an opt-in vulnerability scanner for the open-source ecosystem that’s informed by our experience using Claude to find vulnerabilities during Project Glasswing.
Read more