zlacker

>>nyrikk+(OP)
I think it’s helpful to remember that language models are not producing tokens, they are producing a distribution of possible next tokens. Just because your sampler picks a sequence of tokens that contain incorrect reasoning doesn't mean a useful reasoning trace isn’t also contained within the latent space.

It’s a misconception that transformers reason in token space. Tokens don’t attend to other tokens. High dimensional latents attend to other high dimensional latents. The final layer of a decoder only transformer has full access to entire latent space of all previous latents, the same latents you can project into a distribution of next tokens.

>>valine+r7
So you're saying that the reasoning trace represents sequential connections between the full distribution rather than the sampled tokens from that distribution?

>>jacob0+3k
The lower dimensional logits are discarded, the original high dimensional latents are not.

But yeah, the LLM doesn’t even know the sampler exists. I used the last layer as an example, but it’s likely that reasoning traces exist in the latent space of every layer not just the final one, with the most complex reasoning concentrated in the middle layers.

>>valine+xk
I don't think that's accurate. The logits actually have high dimensionality, and they are intermediate outputs used to sample tokens. The latent representations contain contextual information and are also high-dimensional, but they serve a different role--they feed into the logits.

>>jacob0+co
The dimensionality I suppose depends on the vocab size and your hidden dimension size, but that’s not really relevant. It’s a single linear projection to go from latents to logits.

Reasoning is definitely not happening in the linear projection to logits if that’s what you mean.