Repository navigation
Add embedding-space experiments - #10
Open
peterbjohnson wants to merge 3 commits into
Open
peterbjohnson wants to merge 3 commits into
peterbjohnson wants to merge 3 commits into
Conversation
Nearest neighbours, analogies, learned directions and 2D plots, used to pick course examples showing that directions in embedding space carry meaning. report.md has the recommendations; results.md and plots/ are generated by embeddings.py. No production code changes. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds the embedding-space experiments on the token embeddings of Bengio, GPT-2 and SmolLM2, as educational material and a starting point for the transformer visualisation work. Replaces #9, which GitHub closed when its branch was renamed.
report.md: findings and a ranked shortlist of examples for the courseresults.md: numbers generated byembeddings.pyembeddings.py: runs the experiments and produces the figuresplots/: PCA and direction plots for gender, plural and country to capitalDeployment impact
None to the Lambda. All 11 files are new and sit under
educational_material/embeddings/, which the Dockerfile does not copy and the app does not import. Merging tomainwill still trigger the staging deploy.Testing
Trial merge against
mainwas clean. The test suite passed on #9 at this same commit.embeddings.pywas not re-run on the merged result.🤖 Generated with Claude Code