Glossary · Term

linear representation hypothesis

← all terms

Definition

Plain language

The idea that a model stores each concept as a straight-line direction in its internal numbers, so simple readouts can find it.

As stated in the literature

The conjecture that high-level features are encoded as linear directions in a model's activation space, motivating linear probes and steering vectors as interpretability tools.

Also called: linear representation

Why it matters: If concepts really are stored as simple directions, researchers can read and even adjust what a model is doing with lightweight, understandable tools.

For example, if the idea holds, the notion of 'this text is in French' might live along a single straight direction inside the model that a simple tool can detect.

Heard on the show

“… There's a broader bet behind this called the linear representation hypothesis — the observation that concepts in these models tend to be encoded as directions — which …”
Episode 204 — The Length Estimate Hiding Inside a Word-by-Word Model

Mentioned in 1 episode

  1. 204
    The Length Estimate Hiding Inside a Word-by-Word Model

Related concepts

Related terms