InterpretabilityResearch

Toy Models of Superposition

Sep 14, 2022
Read Paper

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

Patterns and problems in emerging multiagent systems

Here, we identify a few examples of behavioral tendencies in current frontier models and show how they can produce unexpected systemic failures, in hopes of starting a conversation about mitigating these risks.

Read more

Reviewing the evidence on worker retraining programs

We're sharing a review of the evidence on worker retraining programs, coauthored by independent researcher David Roodman and Anthropic's Maxim Massenkoff.

Read more

Learning more about Claude's mathematical capabilities

An unreleased research version of Claude has made strides on a problem related to the Riemann hypothesis. It improved a longstanding lower bound for the fraction of zeros of the Riemann zeta function that satisfy the hypothesis, increasing it from 41.6% to 67.2%.

Read more