https://github.com/ndif-team/nnsight-website
The nnsight website, which explains and documents the open-source nnsight API
https://github.com/ndif-team/nnsight-website
interpretability machine-learning tutorials website
Last synced: 6 months ago
JSON representation
The nnsight website, which explains and documents the open-source nnsight API
- Host: GitHub
- URL: https://github.com/ndif-team/nnsight-website
- Owner: ndif-team
- Created: 2023-10-21T22:15:51.000Z (over 2 years ago)
- Default Branch: docs
- Last Pushed: 2025-12-19T22:30:03.000Z (7 months ago)
- Last Synced: 2025-12-22T09:34:20.491Z (6 months ago)
- Topics: interpretability, machine-learning, tutorials, website
- Language: Jupyter Notebook
- Homepage: https://nnsight.net/
- Size: 106 MB
- Stars: 3
- Watchers: 2
- Forks: 2
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# NNsight Docs
Check the [wiki](https://github.com/ndif-team/nnsight-website/wiki) for all the info on how to update the docs using Sphinx.
In short, this build is managed with Github Actions. Any changes you make to the source files will be built and automatically published to Github pages and served.
## Keeping in sync with NNsight
In order to build and publish this site, the correct NNsight version needs to be released. If that version is not published, things will not work properly.
## Getting Started
This project uses `uv` as a default python environment. You can get started [here](https://docs.astral.sh/uv/getting-started/installation/).
From root, run `uv sync` to set up the required packages. This will install nnsight according to whatever is in `pyproject.toml` and `uv.lock`, so if you need to upgrade it to a specific package, you can do so by editing `pyproject.toml` to reflect the correct version and running `uv sync` again.
Then, start a hotreloading webserver by running `bash run.sh`.