We use a few cookies

Essential cookies keep the library working. With your permission, we'd also like to use analytics to see what's useful and improve the experience. Read our Privacy Policy or Cookie Policy.

Skip to main content
Home/e-Resources/Artificial Intelligence & Machine Learning/Emergent Linear Representations in World Models of Self-Supervised Sequence Models
Conference ProceedingsArtificial Intelligence & Machine Learning

Emergent Linear Representations in World Models of Self-Supervised Sequence Models

2023

Checking your access to this record.

Abstract & Overview

How do sequence models represent their decision-making process?Prior work suggests that Othello-playing neural network learned nonlinear models of the board state (Li et al., 2023a).In this work, we provide evidence of a closely related linear representation of the board.In particular, we show that probing for "my colour" vs. "opponent's colour" may be a simple yet powerful way to interpret the model's internal state.This precise understanding of the internal representations allows us to control the model's behaviour with simple vector arithmetic.Linear representations enable significant interpretability progress, which we demonstrate with further exploration of how the world model is computed.

Cite this record

Neel Nanda, Andrew Lee, MARTIN P. WATTENBERG (2023). Emergent Linear Representations in World Models of Self-Supervised Sequence Models. https://doi.org/10.18653/v1/2023.blackboxnlp-1.2

Copy in another style

Nanda, N., Lee, A., & WATTENBERG, M. P. (2023). Emergent Linear Representations in World Models of Self-Supervised Sequence Models. https://doi.org/10.18653/v1/2023.blackboxnlp-1.2
Author names are used as deposited, so check their order before you submit.

Metadata is harvested from open-access indexes and can be incomplete. Check a citation against the published version before relying on it — see our open access & attribution policy.