update metadata
Browse files
README.md
CHANGED
|
@@ -1,3 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Model Card for MAIRA-2-SAE
|
| 2 |
|
| 3 |
This is a collection of sparse autoencoders (SAEs) trained on the residual stream of layer 15 of [MAIRA-2](https://huggingface.co/microsoft/maira-2), and described in the preprint ['Insights into a radiology-specialised multimodal large language model with sparse autoencoders'](https://arxiv.org/abs/2507.12950), presented at the [Actionable Interpretability Workshop @ ICML 2025](https://actionable-interpretability.github.io/).
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
---
|
| 6 |
# Model Card for MAIRA-2-SAE
|
| 7 |
|
| 8 |
This is a collection of sparse autoencoders (SAEs) trained on the residual stream of layer 15 of [MAIRA-2](https://huggingface.co/microsoft/maira-2), and described in the preprint ['Insights into a radiology-specialised multimodal large language model with sparse autoencoders'](https://arxiv.org/abs/2507.12950), presented at the [Actionable Interpretability Workshop @ ICML 2025](https://actionable-interpretability.github.io/).
|