Manifold Steering from a Natural State is Effective and Generalizable, but Relies on Model Accuracy
Source ↗
👁 0
💬 0
tl;dr I continue work to apply Goodfire lab's manifold steering methods to the Gemma-2-2b model's natural state, both in raw residual space and in the space produced by Anthropic's pre-trained CLT features. I find that the model's natural residual state can be directly projected onto a pre-computed manifold and gradually steered to produce day-of-the-week tokens in the expected order on two sets of prompt templates, though the results are hindered by Gemma-2-2b's inaccuracy (43.5% correct) on ma
Comments (0)