Back to News
Advertisement
Advertisement

⚡ Community Insights

Discussion Sentiment

100% Positive

Analyzed from 246 words in the discussion.

Trending Topics

#lens#model#steering#bias#author#basically#layer#able#few#more

Discussion (6 Comments)Read Original on HackerNews

lwarfieldabout 1 hour ago
If the author would like, I self computed a j lens for the 27b version of the qwen model. I used it for my own exploration in this area, and can share it if you want.
schmorptronabout 1 hour ago
I'm not the author, but I would like! Is it feasible to run on the same hardware as the 27b model itself?
lwarfieldabout 1 hour ago
The using a J lens is super cheap compared to inference. You basically add a single matrix multiply per layer. You probably wouldn't even notice the overhead in a good implementation.

You should even be able to create a j lens from scratch, but it might take a while. I was able to do it in a few hours on an H100. Creating the J lens is basically the equivalent of calculating a few thousand training steps for a model (256,000 backprops in my case). I've got more details in a blog post:

https://blog.lwarfield.dev/layer-scope/

I'm currently at work and can't those matrixes up until I get home. I'll update this comment with a link later.

jasonjmcgheeabout 1 hour ago
Fwiw you can just Google this for a model and often someone has done it

https://huggingface.co/eyes-ml/Qwen3.8-27B_jacobian-lens

a2ff6eeb0about 1 hour ago
This sounds like a great foundation for an adtech startup.

If you provide free chatbot services, but sell advertisers bids on which steering vectors to use to bias towards products, based on an embedding of the prompt, I bet you'd make a ton of money. For example, Coca Cola would bid on prompts about drinks, and bias towards mentioning Coke products.

I wonder if you could also use a similar method to do product placement in GenAI images and videos, and whether ad revenue would be enough to offset the price of generation. Some ad bids can go pretty high...

jasonjmcghee30 minutes ago
Steering can degrade and bias output

Even with basic experiments I've done, it frequently introduces much more hallucination etc and allowing arbitrary steering...

Not to mention you just can't trust a model's judgement if the highest bidder chooses what it thinks