Skip to content

docs: fix duplicate 'of' in normalize_attention_token_scalars docstring #32

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
LeSingh1 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs: fix duplicate 'of' in normalize_attention_token_scalars docstring #32

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion neuron_explainer/activation_server/read_routes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -344,7 +344,7 @@ def normalize_attention_token_scalars(
a. one way to summarize is to compute a summary statistic on the "scalars in", which are
the list of floats associated to each token.
b. the other way is to compute a summary statistic on the "scalars out", which are the
ith entry in each list of of floats that contains an ith entry.
ith entry in each list of floats that contains an ith entry.
i. one summary statistic used is the "total", or sum of all scalars in or out
ii. another summary statistic used is the "max", or maximum of all scalars in or out

Expand Down