Manifold Steering from a Natural State is Effective and Generalizable, but Relies on Model Accuracy

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.

← Back to all developments · Signals are a development reported by more than one source. See the methodology.