Our overall best guess is that an important role of early MLPs is to act as a “multi-token embedding”, that selects^[1] the right unit of analysis from the most recent few tokens (e.g. a name) and converts this to a representation (i.e. some useful meaning encoded in an activation). We can recover different attributes of that unit (e.g. sport played) by taking linear projections, i.e. there are linear representations of attributes. Though we can’t rule it out, our guess is that there isn’t much more interpretable structure (e.g. sparsity or meaningful intermediate representations) to find in the internal mechanisms/parameters of these layers. For future mech interp work we think it likely suffices to focus on understanding how these attributes are represented in these multi-token embeddings (i.e. early-mid residual streams on a multi-token entity), using tools like probing and sparse autoencoders, and thinking of early MLPs similar to how we think of the token embeddings, where the embeddings produced may have structure (e.g. a “has space” or “positive sentiment” feature), but the internal mechanism is just a look-up table with no structure to interpret.

You may be interested in works like REMEDI and Identifying Linear Relational Concepts in Large Language Models.

Unsupervised Feature Detection There is a rich literature on unsupervised feature detection in neural networks.

It might be interesting to add (some of) the literature doing unsupervised feature detection in GANs and in diffusion models (e.g. see recent work from Pinar Yanardag and citation trails). 

Related, I wonder if instead of / separately from the L2 distance, using something like a contrastive loss (similarly to how it was used in NoiseCLR or in LatentCLR) might produce interesting / different results.

"Training setups where we train generally powerful AIs with deep serial reasoning (similar to the internal reasoning in a human brain) for an extremely long time on rich outcomes based RL environment until these AIs learn how to become generically agentic and pursue specific outcomes in a wide variety of circumstances."

My intuition goes something like: this doesn't matter that much if e.g. it happens (sufficiently) after you'd get ~human-level automated AI safety R&D with safer setups, e.g. imitation learning and no/less RL fine-tuning. And I'd expect, e.g. based on current scaling laws, but also on theoretical arguments about the difficulty of imitation learning vs. of RL, that the most efficient way to gain new capabilities, will still be imitation learning at least all the way up to very close to human-level. Then, the closer you get to ~human-level automated AI safety R&D with just imitation learning the less of a 'gap' you'd need to 'cover for' with e.g. RL. And the less RL fine-tuning you might need, the less likely it might be that the weights / representations change much (e.g. they don't seem to change much with current DPO). This might all be conceptually operationalizable in terms of effective compute.

Currently, most capabilities indeed seem to come from pre-training, and fine-tuning only seems to 'steer' them / 'wrap them around'; to the degree that even in-context learning can be competitive at this steering; similarly, 'on understanding how reasoning emerges from language model pre-training'.

As others have hinted at/pointed out in the comments, there is an entire science of deep learning out there, including on high-level (vs. e.g. most of low-level mech interp) aspects that can be highly relevant to alignment and that you seem to not be aware of/dismiss. E.g. follow the citation trail of An Explanation of In-context Learning as Implicit Bayesian Inference.

Related - I'd be excited to see connectome studies on how mice are mechanistically capable of empathy; this (+ computational models) seems like it should be in the window of feasibility given e.g. Towards a Foundation Model of the Mouse Visual Cortex: 'We applied the foundation model to the MICrONS dataset: a study of the brain that integrates structure with function at unprecedented scale, containing nanometer-scale morphology, connectivity with >500,000,000 synapses, and function of >70,000 neurons within a ∼ 1mm³ volume spanning multiple areas of the mouse visual cortex. This accurate functional model of the MICrONS data opens the possibility for a systematic characterization of the relationship between circuit structure and function.' 

The computational part could take inspiration from the large amounts of related work modelling other brain areas (using Deep Learning!), e.g. for a survey/research agenda: The neuroconnectionist research programme.

Partial convergence between language models and brains and evolutionary analogy

Excited to see people thinking about this! Importantly, there's an entire ML literature out there to get evidence from and ways to [keep] study[ing] this empirically. Some examples of the existing literature (also see Path dependence in ML inductive biases and How likely is deceptive alignment?): Linear Connectivity Reveals Generalization Strategies - on fine-tuning path-dependance, The Grammar-Learning Trajectories of Neural Language Models (and many references in that thread), Let's Agree to Agree: Neural Networks Share Classification Order on Real Datasets - on pre-training path-dependance. I can probably find many more references through my boorkmarks, if there's an interest for this.