grantmaking.ai Launch Round
Social scientists mostly study latent constructs we cannot see directly. Institutions, norms, beliefs, ideology. Most of our training is about that problem: how to pin one down, how to build a measure for it, and how to check whether the measure means what we say it means. Now many of us work with language models. They label our texts, build our software, and are sometimes used as synthetic respondents. Most of the time we have no idea what happens between the prompt and the output — or whether the output means what we think it does. To the best of my knowledge, there is no accessible, hands-on book teaching mechanistic interpretability, with its premises and perils, to social scientists.
I have started that book to teach a social scientist what they can do to a model. I envision it as a short book, about 30,000 words, and I aim to publish it in an open-access way within a year with a publisher. The working draft is already public at github.com/tapanyemre/anthropology-of-machines, licensed CC BY-NC-SA / MIT.
I divided the content into three sections: observation, intervention, and validation. Observation tells you what you can find. Intervention tells you what the model actually uses. Validation tells you how you know either one showed you what you think it did. Alongside intuitive explanations and engagement with state-of-the-art work, I planned that every methods chapter would end the same way: what does this technique let you claim, and what does it not? The hands-on parts, wherever possible, do not require a personal GPU. That is required if we want the tools accessible to the ones who have the theory and the interest but not the resources.
Chapters will appear when they become readable, not when they are finished, so readers can follow the history of my writing and keep me honest. Readers can also contribute to the review process by pointing out missing or mistaken parts.
I did not start with those questions. I came to this by a side door. In summer 2025 I led the programming sessions of the AIDE summer program at Northeastern's Ethics Institute. One week, a guest lecturer from the NDIF team taught the logit lens — how a language model builds its prediction of the next word, layer by layer — through a library called nnsight, which let us reach inside a model running on their GPUs. Nobody in the room needed a GPU. That week changed what I thought these systems were. A model is not a black box anymore. It is just unread. Learning to read it is the hard part. In November 2025, David Bau emailed me about Neural Mechanics, a full semester of mechanistic interpretability. As the only political scientist invited, I proposed a project on the political ideology of models; it is a working paper now, and the book will contain this study as a worked case, from question to what the result licenses. I took notes the whole time, mostly about what I had to translate. This book is growing out of those notes. Though I am the solo author, I will make it open to everyone who would like to review and check the accuracy of claims.
A book without an audience will be only self-reflections of the author. When I was starting out in computational social science, I co-founded SICSS Istanbul, a two-week summer institute that trained around twenty early-career social scientists a year from 2019 to 2023, and I went back to teach there as a guest lecturer in 2026. With the same motivation, last fall I ran two afternoon workshops on the mechanics of LLMs and a hands-on guide to using them, funded by a small grant, and it brought an interdisciplinary team of social scientists together to learn the material I gathered from computer scientists. So when the manuscript and its hands-on tutorials are done and ready to teach — I expect by summer 2027 — I plan to organize a week-long bootcamp, open to both social scientists and computer scientists, to sit and work on their own projects while learning the tools and the intuition behind them.
Almost all of this is time. I am in my final year of a PhD, and the money buys months in which writing the book is the work rather than the thing I get to after everything else. The stipend is $3,000 a month in living costs. There is no compute line: the hands-on material is designed to run without a personal GPU, on Neuronpedia and NDIF's shared infrastructure, so what a reader needs is a browser and what I need is time.
Ideal — $33,000. Eight months of stipend ($24,000) plus the bootcamp ($9,000).
The eight months carry the manuscript from its current state — preface public, chapters outlined — to a finished draft: the three method sections, the worked case, and the hands-on tutorials, all published openly as they are written.
The $9,000 covers a week-long bootcamp for roughly twenty participants, open to social scientists and computer scientists together. Roughly: $5,000 in travel and accommodation support so people who are not local can attend, $2,500 for food across the week, and $1,500 for a teaching assistant. I have run this kind of thing before on a much smaller budget; the travel support is the line that decides whether it reaches beyond one city.
Minimum — $12,000. About one semester, part-time. It funds the first section of the book, on observation — the tools for finding what is inside a model — written and published openly. The bootcamp would not happen at this level, and the rest of the book would continue at the pace it is going now.
In between: $24,000 covers the full eight months and the complete manuscript, without the bootcamp.
If none of it is funded, the book still happens — on nights and weekends, which realistically means twelve to eighteen months instead of eight, finished after my PhD rather than alongside it. The bootcamp probably does not happen at all.