diff --git a/.github/workflows/publish-book.yml b/.github/workflows/publish-book.yml
index ba81c24..0a12f3b 100644
--- a/.github/workflows/publish-book.yml
+++ b/.github/workflows/publish-book.yml
@@ -21,7 +21,7 @@ jobs:
python -m pip install --upgrade pip
python -m pip install -e .
python -m pip install .[docs]
- pip install jupyter-book sphinxcontrib-mermaid
+ pip install jupyter-book sphinxcontrib-mermaid numpydoc
- name: Build the book
run: |
diff --git a/README.md b/README.md
index dc9a70f..df982dc 100644
--- a/README.md
+++ b/README.md
@@ -1,8 +1,8 @@
# CEBRA-Lens
-## A python library for mechanistic interpretability of CEBRA models
+
-
+A python library for mechanistic interpretability of CEBRA models
**CEBRA-Lens** is a Python library for analyzing and interpreting neural representations learned by models trained with [CEBRA](https://github.com/AdaptiveMotorControlLab/cebra). It provides tools for mechanistic interpretability, allowing users to probe, visualize, and understand the structure of learned embeddings. The library is designed to support in-depth analysis of representational geometry, feature selectivity, and latent space dynamics in neuroscience and beyond. 👋 We welcome contributions and will continue to expand the library in the coming years.
@@ -18,13 +18,13 @@ conda create -n CEBRAlens python=3.12
conda activate CEBRAlens
conda install -c conda-forge pytables==3.8.0
-# install PyTorch with your desired CUDA version (or for CPU only)- check their website: https://pytorch.org/get-started/locally/
+# install PyTorch with your desired CUDA version - check their website: https://pytorch.org/get-started/locally/
# example: GPU version of pytorch for CUDA 11.3
conda install pytorch cudatoolkit=11.3 -c pytorch
# install CEBRA and CEBRA-lens
pip install --pre 'cebra[datasets,demos]'
-pip install -- cebra_lens
+pip install --pre cebra_lens
```
## 🦓🔍 Analysis Methods
@@ -65,7 +65,9 @@ These analyses quantify the change in the distance calculated per layer in a mod
- inter-class distance
- inter-repetition distance (only relevant if the model was trained on a dataset where there is repeating stimuli)
-
+
+
+
# Demo
diff --git a/docs/docs/images/abstractfig.png b/docs/docs/images/abstractfig.png
deleted file mode 100644
index 2bf2925..0000000
Binary files a/docs/docs/images/abstractfig.png and /dev/null differ
diff --git a/docs/docs/images/zebra.png b/docs/docs/images/zebra.png
deleted file mode 100644
index 8328e76..0000000
Binary files a/docs/docs/images/zebra.png and /dev/null differ