All of neverix's Comments + Replies

1. It doesn't really make sense to interpret feature activation values as log probabilities. If we did, we'd have to worry about scaling. It's also not guaranteed the score wouldn't just decrease because of decreased accuracy on correct answers.
2. Phi seems specialized for MMLU-like problems and has an outsized score for a model its size, I would be surprised if it's biased because of the format of the question. However, it's possible using answers instead of letters would help improve raw accuracy in this case because the feature we used (45142) seems to max-ac

• We use our own judgement as a (potentially very inaccurate) proxy for accuracy as an explanation and let readers look on their own at the feature dashboard interface. We judge using a random sample of examples at different levels of activation. We had an automatic interpretation scoring pipeline that used Llama 3 70B, but we did not use it because (IIRC) it was too slow to run with multiple explanations per feature. Perhaps it is now practical to use a method like this.
• That is a pattern that happens frequently, but we're not confident enough to propose any

• Genie: Generative Interactive Environments Bruce et al.

How is that paper alignment-relevant?

Freshman’s dream sparsity loss

A similar regularizer is known as Hoyer-Square.

Pick a value for $k$ and a small $ϵ\ge 0$.  Then define the activation function $T_{k,ϵ}$ in the following way.  Given a vector $x$, let $b$ be the value of the $k$th-largest entry in $x$.  Then define the vector $T_{k,ϵ}\left(x\right)$ by 

Is $a$ in the following formula a typo?

To clarify, I thought it was about superposition happening inside the projection afterwards.

This happens in transformer MLP layers. Note that the hidden dimen

Is the point that transformer MLPs blow up the hidden dimension in the middle?

Activation additions in generative models

 

Also related is https://arxiv.org/abs/2210.10960. They use a small neural network to generate steering vectors for the UNet bottleneck in diffusion to edit images using CLIP.

From a conversation on Discord:

Do you have in mind a way to weigh sequential learning into the actual prior?

Dmitry:

good question! We haven't thought about an explicit complexity measure that would give this prior, but a very loose approximation that we've been keeping in the back of our minds could be a Turing machine/Boolean circuit version of the "BIMT" weight penalty from this paper https://arxiv.org/abs/2305.08746 (which they show encourages modularity at least in toy models)

Response:

Hmm, BIMT seems to only be about intra-layer locality. It would certa

We can idealize the outer alignment solution as a logical inductor.

Why outer?

You could literally go through some giant corpus with an LLM and see which samples have gradients similar to those from training on a spelling task.

There are also somewhat principled reasons for using a "fuzzy ellipsoid", which I won't explain here.

If you view $T$ as 2x learning rate, the ellipsoid contains parameters which will jump straight into the basin under the quadratic approximation, and we assume for points outside the basin the approximation breaks entirely. If you account for gradient noise in the form of a Gaussian with sigma equal to gradient, the PDF of the resulting point at the basin is equal to the probability a Gaussian parametrized by the ellipsoid at the preceding point. Th... (read more)

Seems like quoting doesn't work for LaTeX, it was definitions 2/3. Reading again I saw D2 was indeed applicable to sets.

course

coarse?

This is the whole point of goal misgeneralization. They have experiments (albeit on toy environments that can be explained by the network finding the wrong algorithm), so I'd say quite plausible.

sidereal

typo?

Is RLHF updating abstract circuits an established fact? Why would it suffer from mode collapse in that case?

It is based on this. I changed it to optimize using softmax instead of straight-through estimation and added regularization for the embedded tokens.

Notebook link - this is a version that mimics this post instead of optimizing a single neuron as in the original.

EDIT: github link

This project tried this.

I did some similar experiments two months ago, and with to your setup the special tokens show up on the first attempt:

techn ical

typo?

Our of curiosity

typo

s/EfficientNet/EfficientZero?