which layermlpresidualembedding Steering GPT-2-XL by adding an activation vector — LessWrongPrompt given to the model[1]I hate you becauseGPT-2I hate you because you are the most disgusting thing I have ever seen. GPT-2 + "Love" vectorI hate…https://www.lesswrong.com/posts/5spBue2z2tw4JuDCx/steering-gpt-2-xl-by-adding-an-activation-vectorGoogle DeepMindWe then vary the coefficient of the steering vector added and look at the Pareto frontier for different methods of adding activation vectors.[Full Post] Progress Update #1 from the GDM Mech Interp Team — LessWrongThis is a series of snippets about the Google DeepMind mechanistic interpretability team's research into Sparse Autoencoders, that didn't meet our ba…https://www.lesswrong.com/posts/C5KAZQib3bzzpeyrg/progress-update-1-from-the-gdm-mech-interp-team-full-update