Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models Adam Karvonen Independent Benjamin Wright
–Neural Information Processing Systems
What latent features are encoded in language model (LM) representations?
Neural Information Processing Systems
Oct-10-2025, 10:30:48 GMT
- Country:
- Asia > Singapore (0.04)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- North America > United States
- Massachusetts > Hampshire County
- Amherst (0.04)
- Amherst Center (0.04)
- Massachusetts > Hampshire County
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (1.00)
- Research Report
- Industry:
- Leisure & Entertainment > Games > Chess (0.30)
- Technology: