Thanks a lot for this post, I found it very helpful.

There exists a single direction which contains all linearly available information Previous work has found that, in most datasets, linearly available information can be removed with a single rank-one ablation by ablating along the difference of the means of the two classes.

The specific thing that you measure may be more a fact about linear algebra rather than a fact about LLMs or CCS.

For example, let's construct data which definitely has two linearly independent dimension that are each predictive of whether a point is positive or negative. I'm assuming here that positive/negative exactly corresponds to true/false for convenience (i.e., that all the original statements happened to be true), but I don't think it should matter to the argument.

# Initialize the dataset
p = np.random.normal(size=size)
n = np.random.normal(size=size)

# In the first and second dimensions, they can take values -1, -.5, 0, .5, 1
# The distributions are idiosyncratic for each, but all are predictive of the truth
# label
standard = [-1, -.5, 0, .5, 1]
p[:,0] = np.random.choice(standard, size=(100,), replace=True, p=[0, .1, .2, .3, .4])
n[:,0] = np.random.choice(standard, size=(100,), replace=True, p=[.6, .2, .1, .1, .0])
p[:,1] = np.random.choice(standard, size=(100,), replace=True, p=[0, .05, .05, .1, .8])
n[:,1] = np.random.choice(standard, size=(100,), replace=True, p=[.3, .3, .3, .1, .0])

Then we can plot the data. For the unprojected data plotted in 3-d, the points are linearly classifiable with reasonable accuracy in both those dimensions.

But then we perform the mean projection operation given here (in case I have any bugs!)

def project(p, n):
  # compute the means in each dim
  p_mean = np.mean(p, axis=0)
  n_mean = np.mean(n, axis=0)

  # find the direction
  delta = p_mean - n_mean
  norm = np.linalg.norm(delta, axis=0)
  unit_delta = delta / norm

  # project
  p_proj = p - np.expand_dims(np.inner(p, unit_delta),1) * unit_delta
  n_proj = n - np.expand_dims(np.inner(n, unit_delta),1) * unit_delta
  return p_proj, n_proj

And after projection there is no way to get a linear classifier that has decent accuracy.

Or looking at the projection onto the 2-d plane to make things easier to see:

Note also that this is all with unnormalized raw data, doing the same thing with normalized data gives a very similar result with this as the unprojected:

and these projected figures:

FWIW, I'm like 80% sure that Alex Mennen's comment gives mathematical intuition behind these visualizations, but it wasn't totally clear to me, so posting these in case it is clearer to some others as well.

Thanks for the thought provoking post! Some rough thoughts:

Modelling authors not simulacra

Raw LLMs model the data generating process. The data generating process emits characters/simulacra, but is grounded in authors. Modelling simulacra is probably either a consequence of modelling authors or a means for modelling authors.

Authors behave differently from characters, and in particular are less likely to reveal their dastardly plans and become evil versions of themselves. The context teaches the LLM about what kind of author it is modelling, and this informs how highly various simulacra are weighted in the distribution.

Waluigis can flip back

At a character level, there are possible mechanisms. Sometimes they are redeemed in a Damascene flash. Sometimes they reveal that although they have appeared to be the antagonist the whole time, they were acting under orders and making the ultimate sacrifice for the greater good. From a purely narrative perspective, it’s not obvious that waluigi is the attractor state.

But at an author-modelling level this is even more true. Authors are allowed to flip characters around as they please, and even to have them wake from dream sequences. Honestly most authors write pretty inconsistent characters most of the time, consistent characterisation is low probability on the training distribution. It seems hard to make it really low probability that a piece of text is the sort of thing written by an author who would never do something like this.

There is outside-text for supervised models

Raw LLMs don’t have outside-text. But supervised models totally do, in the shape of your supervision signal which isn’t textual at all, or just hard-coded math. In the limit, for example, your supervision signal can make your model always emit “The cat sat on the mat” with perfect reliability.

However, it is true that you might need some unusual architectural choices to make this robust. Nothing is ‘external’ to the residual stream unless you force it to be with an architecture choice (e.g., by putting it in the final weight layer). And generally the more outside-texty something is the less flexible and amenable to complex reasoning and in-context learning it seems likely to be.

Question: how much of this is specifically about good/evil narrative tropes and how much is about it being easier to define opposites?

I’m genuinely quite unsure from the arguments and experiments so far how much this is a point that “specifying X makes it easy to specify not-X” and how much is “LLMs are trained on a corpus that embeds narrative tropes very deeply (including ones about duality in morally-loaded concepts)”. I think this is something that one could tease apart with clever design.

I'm not sure how serious this suggestion is, but note that:

1. It involves first training a model to be evil, running it, and hoping that you are good enough at jailbreaking to make it good rather than make it pretend to be good. And then to somehow have that be stable.
2. The opposite of something really bad is not necessarily good. E.g., the opposite of a paperclip maximiser is... I guess a paperclip minimiser? That seems approximately as bad.

This doesn't seem to disagree with David's argument? "Accident" implies a lack of negligence. "Not taken seriously enough" points at negligence. I think you are saying that non-negligent but "painfully obvious" harms that occur are "accidents", which seems fair. David is saying that the scenarios he is imagining are negligent and therefore not accidents. These seem compatible.

I understand David to be saying that there is a substantial possibility of x-risk due to negligent but non-intended events, maybe even the majority of the probability. These would sit between "accident" and "misuse" (on both of your definitions).

Thanks, that makes sense.

I think part of my skepticism about the original claim comes from the fact that I'm not sure that any amount of time for people living in some specific stone-age grouping would come up with the concept of 'sapient' without other parts of their environment changing to enable other concepts to get constructed.

There might be a similar point translated into something shard theoryish that's like 'The available shards are very context dependent, so persistent human values across very different contexts is implausible.' SLT in particular probably involves some pretty different contexts.

I also predict that real Eliezer would say about many of these things that they were basically not problematic outputs themselves, just represent how hard it is to stop outputs conditioned on having decided they are problematic. The model seems to totally not get this.

Meta level: let's use these failures to understand how hard alignment is, but not accidentally start thinking that alignment=='not providing information that is readily available on the internet but that we think people shouldn't use'.

Sure, inclusive genetic fitness didn't survive our sharp left turn. But human values did. Individual modern humans are optimizing for them as hard as they were before; and indeed, we aim to protect these values against the future.

Why do you think this? It seems like humans currently have values and used to have values (I'm not sure when they started having values) but they are probably different values. Certainly people today have different values in different cultures, and people who are parts of continuous cultures have different values to people in those cultures 50 years ago.

Is there some reason to think that any specific human values persisted through the human analogue of SLT?