Skip to content

sparse_autoencoder from OpenAI

active 2024-08-082026-05-03 (UTC)

Partial coverage14,546 / 17,650 hourly files (82%) · 2 absent upstream · 3,103 failed, retryable2024-08-062026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
209
Pushes
0
Pull requests
1
Issues
5
Stars
180
Forks
22

Activity over time

Daily event counts in the loaded window

Line chart, 634 days from 2024-08-08 to 2026-05-03. Pushes: 0 total, peak 0 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 5 total, peak 1 in a day. Comments: 1 total, peak 1 in a day. Stars: 180 total, peak 5 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
w10518686262001
Ananya-Joshi2000
Ahndrayo1010
Hambaobao1000
InuyashaYang1000

Recent activity

Latest issues, pull requests and releases

  • Pull request#21Ahndrayo2026-04-01 03:53
  • Issue#19InuyashaYang2025-07-07 05:48
    Layer Normalization is not enabled in train.py, while admitted defaulty in model.py using TopK
  • Issue#13Hambaobao2024-11-12 02:55
    Confusion about the size of SAEs.
  • Issue#18w10518686262024-10-15 01:57
    picture
  • Issue comment#2w10518686262024-09-30 03:37
    Files with activations to run viewer locally
  • Issue#16Ananya-Joshi2024-08-17 07:15
    Trouble Accessing SAEs
  • Issue#16Ananya-Joshi2024-08-15 12:54
    Trouble Accessing SAEs

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 180 stars here means stars gained during the window, not the repo's star count.