diff --git a/pyhealth/interpret/methods/baseline.py b/pyhealth/interpret/methods/baseline.py
index 67629c516..8c00570c1 100644
--- a/pyhealth/interpret/methods/baseline.py
+++ b/pyhealth/interpret/methods/baseline.py
@@ -44,7 +44,7 @@ class RandomBaseline(BaseInterpreter):
     Examples:
         >>> import torch
         >>> from pyhealth.datasets import create_sample_dataset, get_dataloader
-        >>> from pyhealth.interpret.methods.baseline import Random
+        >>> from pyhealth.interpret.methods import RandomBaseline
         >>> from pyhealth.models import MLP
         >>>
         >>> samples = [
@@ -64,7 +64,7 @@ class RandomBaseline(BaseInterpreter):
         >>> model.eval()
         >>> test_loader = get_dataloader(dataset, batch_size=1, shuffle=False)
         >>>
-        >>> rand_interp = Random(model, random_seed=42)
+        >>> rand_interp = RandomBaseline(model, random_seed=42)
         >>> batch = next(iter(test_loader))
         >>> attributions = rand_interp.attribute(**batch)
         >>> print({k: v.shape for k, v in attributions.items()})
diff --git a/pyhealth/interpret/methods/ensemble_crh.py b/pyhealth/interpret/methods/ensemble_crh.py
index 2a901eb9b..a8889c841 100644
--- a/pyhealth/interpret/methods/ensemble_crh.py
+++ b/pyhealth/interpret/methods/ensemble_crh.py
@@ -47,8 +47,8 @@ class CrhEnsemble(BaseInterpreterEnsemble):
             between successive iterations is below this value.
 
     Example:
-        >>> from pyhealth.interpret.methods import GradientShap, IntegratedGradients, Saliency
-        >>> experts = [GradientShap(model), IntegratedGradients(model), Saliency(model)]
+        >>> from pyhealth.interpret.methods import DeepLift, IntegratedGradients, LimeExplainer
+        >>> experts = [IntegratedGradients(model), DeepLift(model), LimeExplainer(model)]
         >>> ensemble = CrhEnsemble(model, experts, n_iter=30)
         >>> attrs = ensemble.attribute(**batch)
     """