Viewing profile — mayukhdeb

Thanks for the kind words! Happy to know that there are people out there who find this stuff just as interesting as I do.

In this paper, we don't zero out the weights. We remove them.

> Is it that the structure clustered the neurons in such a way that they didn't need to be weighted Yep. Because of the structure, we did not have to compute the output of each wei…

Thank you for sharing this! We'll read through this and update the camera-ready version accordingly for ICLR 2025.

Thank you for your kind words!

Thank you for your kind words! Indeed. The problem with most AI research today is they simply do trial and error with large amounts of compute. No room for taking inspiration from …

Thanks for clarifying your reason for renaming the title. The explanation for the original title is this plot from our publication in ICLR 2025: https://toponets.github.io/webpage_…

If by popular fantasy you mean replicating the functional profiles of the visual and language cortex of the brain, then yes. These ideas in neuroscience are popular, but not fantas…

> the features tend to have greater semantical overlap? This is true. The features closer together now have much stronger semantic overlap. You can watch how the weights self-organ…

It is indeed brain-like in a functional way. Topographic structure is what enables the brain to have low dimensionality and metabolic efficiency. We find that inducing such structu…

We localized "toxic" neurons by contrasting the activations of each neuron for toxic v/s normal texts. It's a method inspired by old-school neuroscience.

Yep. That is exactly the idea here. Our compression method is super duper naive. We literally keep every n-th weight column and discard the rest. Turns out that even after getting …

Indeed. What's cool is that we were able to localize literal "regions" in the GPTs which encoded toxic concepts related to racism, politics, etc. A similar video can be found here:…

The motivation was to induce structure in the weights of neural nets and see if the functional organization that emerges aligns with that of the brain or not. Turns out, it does --…

> The only potential benefit Other benefits: 1. Significantly lower dimensionality of internal representations 2. More interpretable (see: https://toponets.github.io ) > 7B model d…

Our goal was never to optimize for performance. There's a long standing hypothesis that topographic structure in the human brain leads to metabolic efficiency. Thanks to topography…