{"id":18581676,"url":"https://github.com/r2d4/blog-embeddings","last_synced_at":"2025-07-04T16:34:34.853Z","repository":{"id":170224916,"uuid":"646354257","full_name":"r2d4/blog-embeddings","owner":"r2d4","description":"Script to generate embeddings from a blog and use GPT-3.5 to categorize the embedding space","archived":false,"fork":false,"pushed_at":"2024-01-02T21:17:28.000Z","size":2429,"stargazers_count":11,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-06-15T04:46:14.805Z","etag":null,"topics":["bert-embeddings","embeddings","gpt","t-sne"],"latest_commit_sha":null,"homepage":"https://matt-rickard.com/two-years-of-daily-blogging","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/r2d4.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2023-05-28T05:46:13.000Z","updated_at":"2024-07-15T19:30:42.000Z","dependencies_parsed_at":"2024-01-02T23:56:02.441Z","dependency_job_id":"8a560875-26f2-49b1-9124-b43244e22305","html_url":"https://github.com/r2d4/blog-embeddings","commit_stats":null,"previous_names":["r2d4/blog-embeddings"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/r2d4/blog-embeddings","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r2d4%2Fblog-embeddings","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r2d4%2Fblog-embeddings/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r2d4%2Fblog-embeddings/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r2d4%2Fblog-embeddings/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/r2d4","download_url":"https://codeload.github.com/r2d4/blog-embeddings/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r2d4%2Fblog-embeddings/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263577257,"owners_count":23483130,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["bert-embeddings","embeddings","gpt","t-sne"],"created_at":"2024-11-07T00:06:37.434Z","updated_at":"2025-07-04T16:34:34.830Z","avatar_url":"https://github.com/r2d4.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Blog Embeddings\n\nAn analysis of two years of daily blogging on [matt-rickard.com](https://matt-rickard.com). \n\n1. I embedded all my posts using BERT (a transformers model pre-trained on a large corpus of English data). BERT uses 768-dimensional vectors.\n\n2. Then I ran them through t-SNE (t-distributed stochastic neighbor embedding, a fancy way to visualize high-dimensional data by translating them to two dimensions. \n\n3. Finally, I separated the two-dimensional space into equally sized bins and asked GPT-3.5 to develop a category name for each set of post titles. ","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fr2d4%2Fblog-embeddings","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fr2d4%2Fblog-embeddings","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fr2d4%2Fblog-embeddings/lists"}