Skip to yearly menu bar Skip to main content


In-Person Poster presentation / top 5% paper

Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task

Kenneth Li · Aspen Hopkins · David Bau · Fernanda ViĆ©gas · Hanspeter Pfister · Martin Wattenberg

MH1-2-3-4 #40

Keywords: [ world representation ] [ GPT ] [ Deep Learning and representational learning ]


Abstract:

Language models show a surprising range of capabilities, but the source of their apparent competence is unclear. Do these networks just memorize a collection of surface statistics, or do they rely on internal representations of the process that generates the sequences they see? We investigate this question by applying a variant of the GPT model to the task of predicting legal moves in a simple board game, Othello. Although the network has no a priori knowledge of the game or its rules, we uncover evidence of an emergent nonlinear internal representation of the board state. Interventional experiments indicate this representation can be used to control the output of the network and create "latent saliency maps" that can help explain predictions in human terms.

Chat is not available.