interpretability

“In a way these models are implemented in operator language in which they are performing certain things. But the operator language itself is so complex that it's no longer readable in a way. It goes beyond what you could engineer by hand or what you can reverse…”

“And then the release this week sort of lets anyone do it for a set of open source models. So notably maybe the most easy one here is like Gemma two to be. So you can sort of like think of some prompt and you kind of like can explain any like token that the mod…”

“The reason for publishing this is that we think interpretably is important. We think it's tractable, and we think more people should work on it. And so publishing it helps us like accomplish with these goals all these goals, which we think are just like crucia…”

“If you've got really good interp, you can start to reframe neural networks, not as just a tool for automating things that we already know how to do, but as a tool for discovery, as like a lens through which you can see patterns in data that would otherwise Be …”

“Interpretability gives you a set of, I think of it almost as like power user tools for accessing models and doing things with them that you might not have realized you could.”

“When we talk to a lot of computational neuroscientists, they Moved to enter because they were like, look, we have unfettered access to this artificial, intelligent mind. It's so much, you have access to everything. You can run as many ablations and experiments…”

“We really believe that interpretability will unlock the new generation, next frontier of safe and powerful AI models.”

“Usually this is black box, not, not white box in, in, in my understanding in, in current work. So, so not using interpretability, but you can imagine in principle doing, doing, doing something more white box.”