adding a comment to clarify predictive_gradeints (Thanks AT)

GPy/core/gp.py

@@ -241,12 +241,14 @@ class GP(Model):
 
     def predictive_gradients(self, Xnew):
         """
-        Compute the derivatives of the latent function with respect to X*
+        Compute the derivatives of the predicted latent function with respect to X*
 
         Given a set of points at which to predict X* (size [N*,Q]), compute the
         derivatives of the mean and variance. Resulting arrays are sized:
          dmu_dX* -- [N*, Q ,D], where D is the number of output in this GP (usually one).
 
+        Note that this is not the same as computing the mean and variance of the derivative of the function!
+
          dv_dX*  -- [N*, Q],    (since all outputs have the same variance)
         :param X: The points at which to get the predictive gradients
         :type X: np.ndarray (Xnew x self.input_dim)

GPy/kern/_src/stationary.py

@@ -296,6 +296,8 @@ class Exponential(Stationary):
         return -0.5*self.K_of_r(r)
 
 
+
+
 class OU(Stationary):
     """
     OU kernel: