Haoxing Du

Some activations inside Leela Zero for randomly selected boards. tl;dr—We did some interpretability on Leela Zero, a superhuman Go model. With a technique similar to the logit lens, we found that the residual structure of Leela Zero induces a preferred basis throughout network, giving rise to persistent, interpretable channels. By...

Some of Redwood’s current research involves finding specific behaviors that language models exhibit, and then doing interpretability to explain how the model does these behaviors. One example of this is the indirect object identification (IOI) behavior, investigated in a forthcoming paper of ours: given the input When John and Mary...