diff --git a/labml_nn/transformers/fast_weights/__init__.py b/labml_nn/transformers/fast_weights/__init__.py
index 52d4bf3d..0324d4d3 100644
--- a/labml_nn/transformers/fast_weights/__init__.py
+++ b/labml_nn/transformers/fast_weights/__init__.py
@@ -181,7 +181,7 @@ class FastWeightsAttention(Module):
     The model first retrieves the current value
     $\bar{v}^{(i)}$ paired with the key $k^{(i)}$.
     Then stores a combination $v^{(i)}_{new}$
-    of the retrieved value $\bar{v}^{̄(i)}$ and the input $v^{(i)}$.
+    of the retrieved value $\bar{v}^{(i)}$ and the input $v^{(i)}$.
 
     \begin{align}
     k^{(i)}, v^{(i)}, q^{(i)} &=
diff --git a/labml_nn/transformers/positional_encoding.py b/labml_nn/transformers/positional_encoding.py
index f974b096..fdcb99bc 100644
--- a/labml_nn/transformers/positional_encoding.py
+++ b/labml_nn/transformers/positional_encoding.py
@@ -50,7 +50,7 @@ def get_positional_encoding(d_model: int, max_len: int = 5000):
     position = torch.arange(0, max_len, dtype=torch.float32).unsqueeze(1)
     # $2 * i$
     two_i = torch.arange(0, d_model, 2, dtype=torch.float32)
-    # $10000^{\frac{2i}{d_{model}}$
+    # $10000^{\frac{2i}{d_{model}}}$
     div_term = torch.exp(two_i * -(math.log(10000.0) / d_model))
     # $PE_{p,2i} = sin\Bigg(\frac{p}{10000^{\frac{2i}{d_{model}}}}\Bigg)$
     encodings[:, 0::2] = torch.sin(position * div_term)