Update README.md
Browse files
README.md
CHANGED
|
@@ -1,25 +1,48 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
language: en
|
| 3 |
library_name: mlsae
|
| 4 |
license: mit
|
| 5 |
tags:
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
- monology/pile-uncopyrighted
|
| 10 |
---
|
| 11 |
|
| 12 |
-
# mlsae-pythia-160m-deduped-x2-k32-tfm
|
| 13 |
|
| 14 |
-
A Multi-Layer Sparse Autoencoder (MLSAE) trained on the residual stream
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
[monology/pile-uncopyrighted](https://huggingface.co/datasets/monology/pile-uncopyrighted).
|
| 19 |
-
This model includes the underlying transformer.
|
| 20 |
|
| 21 |
-
For more details, see:
|
| 22 |
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: EleutherAI/pythia-160m-deduped
|
| 3 |
language: en
|
| 4 |
library_name: mlsae
|
| 5 |
license: mit
|
| 6 |
tags:
|
| 7 |
+
- arxiv:2409.04185
|
| 8 |
+
- model_hub_mixin
|
| 9 |
+
- pytorch_model_hub_mixin
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# Model Card for tim-lawson/mlsae-pythia-160m-deduped-x2-k32-tfm
|
| 13 |
|
| 14 |
+
A Multi-Layer Sparse Autoencoder (MLSAE) trained on the residual stream activation
|
| 15 |
+
vectors from [EleutherAI/pythia-160m-deduped](https://huggingface.co/EleutherAI/pythia-160m-deduped) with an
|
| 16 |
+
expansion factor of R = 2 and sparsity k = 32, over 1 billion
|
| 17 |
+
tokens from [monology/pile-uncopyrighted](https://huggingface.co/datasets/monology/pile-uncopyrighted).
|
|
|
|
|
|
|
| 18 |
|
|
|
|
| 19 |
|
| 20 |
+
This model is a PyTorch Lightning MLSAETransformer module, which includes the underlying
|
| 21 |
+
transformer.
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
### Model Sources
|
| 25 |
+
|
| 26 |
+
- **Repository:** <https://github.com/tim-lawson/mlsae>
|
| 27 |
+
- **Paper:** <https://arxiv.org/abs/2409.04185>
|
| 28 |
+
- **Weights & Biases:** <https://wandb.ai/timlawson-/mlsae>
|
| 29 |
+
|
| 30 |
+
## Citation
|
| 31 |
+
|
| 32 |
+
**BibTeX:**
|
| 33 |
+
|
| 34 |
+
```bibtex
|
| 35 |
+
@misc{lawson_residual_2024,
|
| 36 |
+
title = {Residual {{Stream Analysis}} with {{Multi-Layer SAEs}}},
|
| 37 |
+
author = {Lawson, Tim and Farnik, Lucy and Houghton, Conor and Aitchison, Laurence},
|
| 38 |
+
year = {2024},
|
| 39 |
+
month = oct,
|
| 40 |
+
number = {arXiv:2409.04185},
|
| 41 |
+
eprint = {2409.04185},
|
| 42 |
+
primaryclass = {cs},
|
| 43 |
+
publisher = {arXiv},
|
| 44 |
+
doi = {10.48550/arXiv.2409.04185},
|
| 45 |
+
urldate = {2024-10-08},
|
| 46 |
+
archiveprefix = {arXiv}
|
| 47 |
+
}
|
| 48 |
+
```
|