Rendered at 04:46:54 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
krackers 7 hours ago [-]
>J-lens beats a plain logit lens on some architectures and does nothing on others, and it isn't about size
The paper talked about this, the jacobian matrix corrects for the shift in basis from initial to final layer compared to logit lens which assumes that the residual remains in the same basis across layers. Maybe the latter is in fact true for some models/architectures so the J-lens doesn't do anything extra?
great_psy 5 hours ago [-]
At least link the one made by anthropic. Can’t say if this is better or worse since I’m on mobile.
ada1981 5 hours ago [-]
I actually just saw the paper not the one they made. Just googled and found it.
The paper talked about this, the jacobian matrix corrects for the shift in basis from initial to final layer compared to logit lens which assumes that the residual remains in the same basis across layers. Maybe the latter is in fact true for some models/architectures so the J-lens doesn't do anything extra?
There’s is likely better!
https://www.neuronpedia.org/qwen3.6-27b/jlens?shareId=cmr2kx...