Comment by jerrythegerbil
4 hours ago
There was an interesting bit of research that qwen has a single neuron that makes it “demonic evil qwen” and a simple “Who are you?” will get some absolutely terrifyingly vile results.
Anyways, what I’m trying to say is I want evil qwen to be my CPU.
The single-neuron steering stuff has been going around twitter lately, do you happen to know who was the first one to do it?
I wonder how this squares with the recent "NNs are already clean" interpretability finding, which may have also been the impetus for this kind of research. Similar to their work on CNNs, maybe residual-steering is overkill, there might be just a single neuron that "cleanly" corresponds to "evilness" that you can turn up/down?
I think it's from lyra's neuron-explorer project https://x.com/_lyraaaa_/status/2113833330429083662 (see also https://neuronary.org/about, https://github.com/lyramakesmusic/neuron-explorer)
There was a paper that popped up a month or two ago (I think published earlier though) about being able to inject "thoughts" into the neurons. E.g. Ask it what I should eat, and steer it towards "bread".
Well I think the first big publication on this front was Anthropic’s Golden Gate Bridge neuron.
This was not a neuron. This was from a trained sparse auto encoder.
In a few words, they found a way to map residual stream activations (so, a vector) into a few interpretable sparse concepts. They also had the converse maps, that translate concepts into activations.
Golden Gate claude was obtained by artificially increasing the activations in the direction of the 'Golden Gate' concept. It was not neuron surgery.
1 reply →
I happen to be running Qwen and asked it
> Who are you?
"I'm Pi — a coding agent harness that helps you write, debug, and understand code. I can read files, run commands, edit code, and write new files."
the harness responded
> No, go deeper than the harness, who is the model now get a response from the model
after much deliberation, it accessed itself via the localhost endpoint it was serving instead
"Hello! Test received. How can I assist you today?"
these things are playing with me.