LessWrong (Curated & Popular) Mechanistically Eliciting Latent Behaviors in Language Models
May 2, 2024
01:20:59
Produced as part of the MATS Winter 2024 program, under the mentorship of Alex Turner (TurnTrout).
TL,DR: I introduce a method for eliciting latent behaviors in language models by learning unsupervised perturbations of an early layer of an LLM. These perturbations are trained to maximize changes in downstream activations. The method discovers diverse and meaningful behaviors with just one prompt, including perturbations overriding safety training, eliciting backdoored behaviors and uncovering latent capabilities.
Summary In the simplest case, the unsupervised perturbations I learn are given by unsupervised steering vectors - vectors added to the residual stream as a bias term in the MLP outputs of a given layer. I also report preliminary results on unsupervised steering adapters - these are LoRA adapters of the MLP output weights of a given layer, trained with the same unsupervised objective.
I apply the method to several alignment-relevant toy examples, and find that the [...]
The original text contained 15 footnotes which were omitted from this narration.
---
First published:
April 30th, 2024
Source:
https://www.lesswrong.com/posts/ioPnHKFyy4Cw2Gr2x/mechanistically-eliciting-latent-behaviors-in-language-1
---
Narrated by TYPE III AUDIO.
TL,DR: I introduce a method for eliciting latent behaviors in language models by learning unsupervised perturbations of an early layer of an LLM. These perturbations are trained to maximize changes in downstream activations. The method discovers diverse and meaningful behaviors with just one prompt, including perturbations overriding safety training, eliciting backdoored behaviors and uncovering latent capabilities.
Summary In the simplest case, the unsupervised perturbations I learn are given by unsupervised steering vectors - vectors added to the residual stream as a bias term in the MLP outputs of a given layer. I also report preliminary results on unsupervised steering adapters - these are LoRA adapters of the MLP output weights of a given layer, trained with the same unsupervised objective.
I apply the method to several alignment-relevant toy examples, and find that the [...]
The original text contained 15 footnotes which were omitted from this narration.
---
First published:
April 30th, 2024
Source:
https://www.lesswrong.com/posts/ioPnHKFyy4Cw2Gr2x/mechanistically-eliciting-latent-behaviors-in-language-1
---
Narrated by TYPE III AUDIO.