Let's understand Large Language Models better

[dmm]

This is a good starting point:

"A Mathematical Framework for Transformer Circuits", Dec 2021
transformer-circuits.pub/2021/framework/index.html

Comments

[dmm]

Revisiting Neel Nanda lecture (and the paper itself).

~10:00 (anecdotally) an attempt to interpret small visual models on MNIST by Chris Olah did not work, but visual models became more interpretable when they got larger.

In Transformers, smaller models are easier to understand, but this is by no means obvious (says Neel Nanda in that lecture, but who knows how this would change eventually; in any case, the knowledge thus acquired does seem to be transferrable OK to larger models).

[dmm]

~24:50 Ah, this is why we predict not only the next token, but all tokens after all preceding partial contexts.

This is useless at inference, but this works great to parallelize training.

[dmm]

~29:00 it seems that most computations only go through a couple of layers (residual stream gives it the freedom to do this).

(So the bulk of computations are probably shallow, with a bit of "true deepness" sprinkled on top of it.)

[dmm]

~32:00 residual stream is really messy, so interpretation via meaningful paths through the model is the only viable way (thankfully, it works OK).

(perhaps people who conjecture about "holographic storage" within residual stream are right, who knows; one can consider improving it in various ways: a) towards detangling, b) alternatively, towards better holography)

[dmm]

~36:00 privileged bases in vector spaces come from non-linearities (which is why the residual stream tends not to have any privileged basis)

(but, actually, positions are meaningful, so there is still a bit of privileged structure in the residual stream, just (perhaps) not within the embedding vectors (but perhaps even there, if we look closely, who knows))

~37:50 spectrum of how privileged a basis is, rather than a binary privileged vs non-privileged

(the truth is there are traces of various privileges in the residual stream as well)

~39:30 even ADAM privileges everything it interacts with, because of its weirdness ("ADAM sucks" says Neel Nanda, but I don't think it's necessarily so, perhaps this artificial thing is good, who knows(!)).

[dmm]

~43:00 virtual weights - it's not really between layers, it's between attention heads (just see how (if at all) to take into account a particular attention head output by a particular attention head input)

that gives some crude proxy for what's going on

[dmm]

~45:00 there is this weird ambiguity when people only use embedding dimension when they talk about dimensionality of residual stream and omit the context length dimension; I can imagine this might bite us in many ways (not only in confusion, but in leading to wrong conclusions)

[dmm]

I just double-checked his remark about MLP having 4 times more neurons than embedding in https://github.com/karpathy/minGPT/blob/master/mingpt/model.py and yes, it is the case there

(but we need to see how this works with context length, it's not very transparent in the code, which is inconvenient; in MLP it is even less transparent than in the attention layer, where they have to write it explicitly in connection with splitting into attention heads)

[dmm]

53:50 Transformers figure out how to clean-up unnecessary leftovers from residual stream

[dmm]

56:00 he speculates that embedding and unembedding only using a fraction of residual stream dimensionality