Update README.md

README.md

@@ -148,7 +148,7 @@ The control-vectors in this repo were created as an experiment by increasing the
 
 </details>
 
-This means each models' cross-covariance matrix will be the result of `120,000` hidden state samples and this in turn will mean each uses ~10x the hidden state dimension for the largest models.
+This means each models' cross-covariance matrix will be the result of `120,000` hidden state samples and this in turn will mean each uses ~10x the hidden state dimension for the largest models with `hidden_dim = 12288`.
 
 ## Regularisation