update small

README.md

@@ -134,4 +134,4 @@ All layers were trained across all 257 image patches. Below we provide plots dem
 
 ## References
 
-We draw heavily from prior Visual Sparse Autoencoder research work by [Hugo Fry](https://www.lesswrong.com/posts/bCtbuWraqYTDtuARg/towards-multimodal-interpretability-learning-sparse-2) and [Gytis Daujotas](https://www.lesswrong.com/posts/iYFuZo9BMvr6GgMs5/case-study-interpreting-manipulating-and-controlling-clip). We also rely on Autointerpretability research from [Anthropic Circuits Updates](https://transformer-circuits.pub/2024/august-update/index.html), and take the TopKSAE architecture and training methodology from [Scaling and Evaluating Sparse Autoencoders](https://cdn.openai.com/papers/sparse-autoencoders.pdf). We also base all our training and inference on data from the [LAION project](https://laion.ai/laion-400-open-dataset/).
+We draw heavily from prior Visual Sparse Autoencoder research work by [Hugo Fry](https://www.lesswrong.com/posts/bCtbuWraqYTDtuARg/towards-multimodal-interpretability-learning-sparse-2) and [Gytis Daujotas](https://www.lesswrong.com/posts/iYFuZo9BMvr6GgMs5/case-study-interpreting-manipulating-and-controlling-clip). We also rely on Autointerpretability research from [Anthropic Circuits Updates](https://transformer-circuits.pub/2024/august-update/index.html), and take the TopKSAE architecture and training methodology from [Scaling and Evaluating Sparse Autoencoders](https://cdn.openai.com/papers/sparse-autoencoders.pdf). We base all our training and inference on data from the [LAION project](https://laion.ai/laion-400-open-dataset/).