Instructions to use ivanenclonar/non_euclidean_sae with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAELens
How to use ivanenclonar/non_euclidean_sae with SAELens:
# pip install sae-lens from sae_lens import SAE sae, cfg_dict, sparsity = SAE.from_pretrained( release = "RELEASE_ID", # e.g., "gpt2-small-res-jb". See other options in https://github.com/jbloomAus/SAELens/blob/main/sae_lens/pretrained_saes.yaml sae_id = "SAE_ID", # e.g., "blocks.8.hook_resid_pre". Won't always be a hook point ) - Notebooks
- Google Colab
- Kaggle
Add README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: saelens
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# SAEs for use with the SAELens library
|
| 6 |
+
|
| 7 |
+
This repository contains the following SAEs:
|
| 8 |
+
- blocks.0.hook_mlp_out
|
| 9 |
+
|
| 10 |
+
Load these SAEs using SAELens as below:
|
| 11 |
+
```python
|
| 12 |
+
from sae_lens import SAE
|
| 13 |
+
|
| 14 |
+
sae, cfg_dict, sparsity = SAE.from_pretrained("ivanenclonar/non_euclidean_sae", "<sae_id>")
|
| 15 |
+
```
|