Research Interests

Hi! I'm Logan. I wanted to compile a document describing my current interests, in case it increased the likelihood of serendipitous coincidences — someone seeing this site, saying "oh, I'm working on that!" or "oh, I want to do a project like that!" and reaching out. As described before, a website is a long and complex search query (etc).

My main interest right now is mechanistic interpretability. I think mechanistic interpretability is both technically fascinating and philosophically, or something like "for the purposes of general world-modeling, " interesting. As of Spring 2025 I'm working on understanding learning differences in ViTs and ResNets using SAEs (it's for a vision models class, lol). Mechanistic interpretability is my intellectual priority right now, and I want this page to first of all reflect that; this, or adjacent things, is what I mainly want to work on. It's also something I actually have real technical skills in, which makes working on projects in it easier.

Note (May 20): I'm looking work in interpretability, or adjacent fields! Please reach out (me at logan graves dot com) if you (or others you know) are hiring. :)

With that said, here are other research topics I'd totally still be interested in:

  1. Mathematical models of agent coordination
    1. Abstract models (e.g. game theory)
    2. In the wild models (e.g. mechanism design)
    3. Qualitative models (e.g. history)
  2. Computational neuroscience, particularly computational neuroscience projects that draw from effective methodologies from AI (e.g. mechanistic interpretability)
    1. Neuron modeling
    2. Modeling neural circuitry (this one especially)
  3. Intellectual history
    1. 20th century intellectual history; how ideology shaped response to crises
    2. Longer-term undercurrents in human thought, e.g. comparative classics research
  4. Theology in/and mathematics
  5. Cyborgism-y things, e.g. what Neuralink is doing, as well as Chalmers and Clark's "Extended mind"

< Home