Sholto Douglas: belief

Transcript context

…I think images are also in some ways just easier to interpret than text. There’s Chris Olah’s interpretability work on AlexNet and these other models. In the original AlexNet paper, they actually split the model into two GPUs just because GPUs were so bad back then relatively speaking, they were still great at the time. That was one of the big innovations of the paper. They find branch specialization. And there's a Distill Pub article on this where colors go to one GPU and Gabor filters and line detectors go to the other. Like the floppy ear detector, that was just a neuron in the model that you could make sense of. You didn't need to disentangle superposition. So just different data set, different modality. I think a wonderful research project to do, if someone is out there listening to this, would be to try and take some of the techniques that Trenton's team has worked on and try and disentangle the neurons in the Mistral paper, Mixtral model, which is open source. I think that's a fantastic thing to do. It feels intuitively like there should be. They didn't demonstrate any evidence that there is. In general, there’s also a lot of evidence that there should be specialization. Go and see if you can find it. Anthropic has published most of their stuff on, as I understand it, dense models. Basically, that is a wonderful research project to try. Given Dwarkesh's success with the Vesuvius Challenge, we should be pitching more projects because they will be solved if we talk about them on the podcast.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.