Papers by Shruti Joshi
From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts? (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to evaluate features disentangle concepts from activations of neural networks are limited by their quality . current methods for concept identification and steering are sparse autoencoders, but they are not reliable. |
| Approach: | They propose to evaluate how well featurization methods disentangle one concept from another . they use sentiment, domain, voice, and tense to steer these features . |
| Outcome: | The proposed evaluations show that featurization methods are insufficient to establish steering selectivity . the results suggest that steering a feature affects many concepts despite a near absence of interaction effects. |