Transformer language models (LMs) have been shown to represent concepts as directions in the latent space of hidden activations. However, for any human-interpretable concept, how can we find its direction in the latent space? We present a technique called linear relational concepts (LRC) for finding concept directions corresponding to human-interpretable concepts by first modeling the relation between subject and object as a linear relational embedding (LRE). We find that inverting the LRE and using earlier object layers results in a powerful technique for finding concept directions that outperforms standard black-box probing classifiers. We evaluate LRCs on their performance as concept classifiers as well as their ability to causally change model output.
@article{arxiv.2311.08968,
title = {Identifying Linear Relational Concepts in Large Language Models},
author = {David Chanin and Anthony Hunter and Oana-Maria Camburu},
journal= {arXiv preprint arXiv:2311.08968},
year = {2024}
}