Comments (1)
Done.
from saelens.
Related Issues (20)
- [Proposal] Add Connor and Rob's Attn SAEs to the official `from_pretrained()` list
- Clarify batch size units HOT 1
- [Proposal] add the loading SAE from Huggingface utils to TransformerLens HOT 1
- [Bug Report] make check-ci fails one test on CUDA >= 10.2 HOT 1
- [Proposal] Current session loading process can be very confusing and should be simpler
- [Proposal] Make it easier to diagnose accidental dataset/tokenizer mismatch HOT 1
- [Proposal] We should make a more comprehensive / details contribution guide.
- [Proposal] tidy normalisation code
- [Bug Report] Cannot find `train_batch_size` in `LanguageModelSAERunnerConfig.__init__()` HOT 2
- [Bug Report] evals.py ablates all heads when it needs to ablate only one HOT 3
- [Bug Report] Cannot train on z: interfaces disagree on shape? HOT 3
- [Bug Report] Saved Models Cannot be Loaded HOT 5
- [Bug Report] make check-ci fails with pyright 1.1.366 HOT 1
- [Bug Report] docs: Slack link is broken HOT 2
- [Proposal] Add MLP transcoders HOT 1
- [Proposal] Allow loading TransformerLens models saved locally
- [Bug Report] ActivationsStore fails for models without a tokenizer
- [Proposal] Add note that Windows unsupported HOT 3
- How to reproduce jbloom/Gemma-2b-Residual-Stream-SAEs HOT 6
- How to train SAEs on my own model? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from saelens.