Mapping the Mind of a Large Language Model
Mapping the Mind of a Large Language Model
We have identified how millions of concepts are represented inside Claude Sonnet, one of our deployed large language models. This is the first ever detailed look inside a modern, production-grade large language model.
I often see a lot of people with outdated understanding of modern LLMs.
This is probably the best interpretability research to date, by the leading interpretability research team.
It's worth a read if you want a peek behind the curtain on modern models.
This is a really good science communication article, it describes their work in clear terms (finding structures that relate to abstract concepts, seeing when they are activated and how strengthening and weaking them modifies outputs) and goes into the implications for it. I'm probably going to save this link as a rebuttal for the people who claim LLMs just predict the next word and have no concepts embedded in them.
I doubt that anyone saying that LLM are calculating next word solely based on previous sequence. It's still statistics, regardless of complexity.
Yes, but people forget that our brains, and therefore our minds, are also "simply" statistics, albeit very complex.
There is no mind. It's pretty clear that these people don't understand their own models. Pretending that there's a mind and the other absurd anthropomorphisms doesn't inspire any confidence. Claude is not a person jfc.
You’re reading the title too literally. “Mind” is only mentioned once in the entire article, and that’s in the title.
I think the most interesting thing in this article is the fact that some concepts central to semantics (analogy, connotation) or psychology (bias) kind of emerge naturally in multi layered neural networks of sufficient size. Also that it can sound like different personalities (overconfident, secretive, delusional) if you manipulate the weight or the proximity of features. I'd like to see the same kind of study but for midjourney...
That's a chicken and egg situation tho. Is the bias a result of a mind? Or is it the result of being trained on data with common human biases all put together by humans? Are these traits actually measurable or are we just anthropomorphizing a machine like we do everything else?
I would imagine a similar result. Like how the word “cartoon” activates one particular feature. And if you identify this feature you can control the level of “cartooniness” by tweaking the particular feature.