Activation Scaling for Steering and Interpreting Language Models

Niklas Stoehr, Kevin Du, Vésteinn Snæbjarnarson, Robert West, Ryan Cotterell, Aaron Schein


Abstract
Given the prompt “Rome is in”, can we steer a language model to flip its prediction of an incorrect token “France” to a correct token “Italy” by only multiplying a few relevant activation vectors with scalars? We argue that successfully intervening on a model is a prerequisite for interpreting its internal workings. Concretely, we establish a three-term objective: a successful intervention should flip the correct with the wrong token and vice versa (effectiveness), and leave other tokens unaffected (faithfulness), all while being sparse (minimality). Using gradient-based optimization, this objective lets us learn (and later evaluate) a specific kind of efficient and interpretable intervention: activation scaling only modifies the signed magnitude of activation vectors to strengthen, weaken, or reverse the steering directions already encoded in the model. On synthetic tasks, this intervention performs comparably with steering vectors in terms of effectiveness and faithfulness, but is much more minimal allowing us to pinpoint interpretable model components. We evaluate activation scaling from different angles, compare performance on different datasets, and make activation scalars a learnable function of the activation vectors themselves to generalize to varying-length prompts.
Anthology ID:
2024.findings-emnlp.479
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8189–8200
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.479/
DOI:
10.18653/v1/2024.findings-emnlp.479
Bibkey:
Cite (ACL):
Niklas Stoehr, Kevin Du, Vésteinn Snæbjarnarson, Robert West, Ryan Cotterell, and Aaron Schein. 2024. Activation Scaling for Steering and Interpreting Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 8189–8200, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Activation Scaling for Steering and Interpreting Language Models (Stoehr et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.479.pdf