Papers by David Chanin
Identifying Linear Relational Concepts in Large Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | a technique for finding concept directions for human-interpretable concepts is needed to find their direction in the latent space . a linear relational concept (LRC) can be used to locate concepts in hidden activations . |
| Approach: | They propose a method for finding human-interpretable concepts by inverting a linear relational embedding and using earlier object layers. |
| Outcome: | The proposed method outperforms standard probing classifiers on performance as concept classifier and ability to causally change model output. |