Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- togethercomputer/RedPajama-Data-1T-Sample
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
library_name: transformers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
This is a set of sparse autoencoders (SAEs) trained on the residual stream of [Llama 3 8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) using the 10B sample of the [RedPajama v2 corpus](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-V2), which comes out to roughly 8.5B tokens using the Llama 3 tokenizer. The SAEs are organized by layer, and can be loaded using the EleutherAI [`sae` library](https://github.com/EleutherAI/sae).
|
| 11 |
+
|
| 12 |
+
These are early checkpoints of an ongoing training run which can be tracked [here](https://wandb.ai/eleutherai/sae/runs/7r5puw5z?nw=nwusernorabelrose). They will be updated as the training run progresses. The last upload was at 7,000 steps.
|