Instructions to use chanind/synthetic-model-131k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAELens
How to use chanind/synthetic-model-131k 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 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: saelens
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# Synthetic Model for SAE Training
|
| 6 |
+
|
| 7 |
+
This repository contains a SyntheticModel for use with SAELens.
|
| 8 |
+
|
| 9 |
+
## Model Info
|
| 10 |
+
|
| 11 |
+
- **Number of features**: 131,072
|
| 12 |
+
- **Hidden dimension**: 512
|
| 13 |
+
- **Hierarchy**: Yes
|
| 14 |
+
- Root nodes: 64
|
| 15 |
+
- Total nodes: 131072
|
| 16 |
+
- Max depth: 3
|
| 17 |
+
- **Feature correlation**: Yes (scale 0.2)
|
| 18 |
+
|
| 19 |
+
## Usage
|
| 20 |
+
|
| 21 |
+
```python
|
| 22 |
+
from sae_lens.synthetic import SyntheticModel
|
| 23 |
+
|
| 24 |
+
model = SyntheticModel.from_pretrained("chanind/synthetic-model-131k")
|
| 25 |
+
```
|