What happens with steering vectors to remove biases?

Getting back in the safety field after 4 years feels great. I had a paper on concept distillation where I showed how steering vectors based method did'nt help to debias model since the concepts itself are understood wrongly [Concept distillation, NeurIPS 2023].I am so happy to see the steering vectors work picked up in interpretability and was curious to see how methods like ActAdd would work in this debiasing setting?So, I apply ActAdd to debias a model.Consider Colored-MNIST setting (age-old) ...