Update README.md

README.md

@@ -3,15 +3,21 @@ language: en
 library_name: mlsae
 license: mit
 tags:
-- model_hub_mixin
-- pytorch_model_hub_mixin
+  - model_hub_mixin
+  - pytorch_model_hub_mixin
 datasets:
-- monology/pile-uncopyrighted
+  - monology/pile-uncopyrighted
 ---
 
-A Multi-Layer Sparse Autoencoder (MLSAE) trained on [EleutherAI/pythia-70m-deduped](https://huggingface.co/EleutherAI/pythia-70m-deduped) and [monology/pile-uncopyrighted](https://huggingface.co/datasets/monology/pile-uncopyrighted), with an expansion factor of 1 and $k = 16$.
-For more details, see the [paper](https://arxiv.org/submit/5837813) and the [Weights & Biases project](https://wandb.ai/timlawson-/mlsae).
+# mlsae-pythia-70m-deduped-x1-k16
 
-This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+A Multi-Layer Sparse Autoencoder (MLSAE) trained on the residual stream
+activation vectors from every layer of
+[EleutherAI/pythia-70m-deduped](https://huggingface.co/EleutherAI/pythia-70m-deduped)
+with an expansion factor of 1 and k = 16, over 1 billion tokens from
+[monology/pile-uncopyrighted](https://huggingface.co/datasets/monology/pile-uncopyrighted).
+For more details, see:
 
-- Library: <https://github.com/tim-lawson/mlsae>
+- Paper: <https://arxiv.org/abs/2409.04185>,
+- GitHub repository: <https://github.com/tim-lawson/mlsae>
+- Weights & Biases project: <https://wandb.ai/timlawson-/mlsae>