A tool for visualising token embedding spaces.
Each axis is specified with a positive and negative token. A word list is then projected onto this axis.
See a more detailed explanation here.
Frontend uses D3.js.
Backend uses Python, flask, and gensim.
Deployed on a DigitalOcean VPS.
I was comissioned to create an interactive map of the ecosystem of organisations related to AI safety.
Users can zoom and pan across the map, hover over items for more information, and click on items to see the respective website.
Created with D3.js.
The data is pulled from a Google Sheet so that anyone can suggest updates or corrections.
A webpage with 3D visualisations of the parameter count of notable AI models.
This gives an intuition for the relative sizes of models, and how models are growing over time.
Created with THREE.js and data from Epoch AI
I was commissioned to create animated visualisations of US income over time.
The data preparation and prototyping was done ith Python, Pandas, and pyplot.
The polished visualisations were created with html, and D3.js.
A web interface in the repo allows further customization of the animations.
Litmaps is an early stage startup which builds tools for visualising and discovering scientific papers.
I coded the visualisation logic currently in production.
This involved implementing efficient javascript algorithms for visualisation use-cases and setting up any necessary backend using FastAPI and Python.
More details can be found here.
I animated a snippet from the podcast AXRP to provide an overview of the motivation and content of mechanistic interpretability.
The podcast is a conversation between researcher Neel Nanda and host Daniel Filan.
This was used in a training course and has 5.9k views.
I animated a snippet from the podcast AXRP which illustrates how transformers do modular arithmetic, which was an output of some of Neel Nanda's mechanistic interpretability research.
The podcast is a conversation between researcher Neel Nanda and host Daniel Filan.
I'm building a three dimensional sandbox game with hand drawn sprites.
Work in progress.
Created with THREE.js.