🪄 Interpreto is an interpretability toolbox for LLMs
active 2025-06-04 → 2026-08-12 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 435 days from 2025-06-04 to 2026-08-12. Pushes: 302 total, peak 9 in a day. Pull requests: 41 total, peak 2 in a day. Issues: 25 total, peak 5 in a day. Comments: 140 total, peak 10 in a day. Stars: 60 total, peak 6 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| AntoninPoche | 304 | 155 | 20 | 65 |
| fanny-jourdan | 160 | 53 | 6 | 49 |
| github-actions[bot] | 27 | 25 | 2 | 0 |
| thomas-mullor | 23 | 14 | 4 | 1 |
| cofri | 18 | 6 | 2 | 7 |
| chatgpt-codex-connector[bot] | 15 | 0 | 0 | 12 |
| HugoDeBosschere | 11 | 11 | 0 | 0 |
| clayecharlotte | 10 | 9 | 0 | 1 |
| Raphael-Bernas | 8 | 7 | 1 | 0 |
| fredericboisnard | 6 | 2 | 2 | 1 |
| Copilot | 5 | 0 | 0 | 2 |
| ClementBM-CLB | 4 | 0 | 2 | 1 |
| NLP-traveller | 2 | 0 | 0 | 0 |
| camillebrl | 1 | 0 | 1 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#141github-actions[bot]2026-04-06 09:18
- Pull request#134camillebrl2026-03-10 08:18
- Pull request#125AntoninPoche2026-02-16 17:54
- Issue#127AntoninPoche2026-02-11 09:52Memory management for generation.
- Issue comment#126AntoninPoche2026-02-10 14:45Fix links of tutorials in readme and doc
- Issue comment#122AntoninPoche2026-01-26 08:58chore(vendor): sync overcomplete subset
- Pull request#122github-actions[bot]2026-01-26 08:46
- Pull request#121AntoninPoche2026-01-22 08:24
- Issue comment#120AntoninPoche2026-01-22 08:17The notebook attribution_walkthrough.ipynb is missing an import.
- Pull request#118AntoninPoche2026-01-20 08:52
- Pull request#119fanny-jourdan2026-01-19 23:42
- Pull request#117AntoninPoche2026-01-18 20:02
- Pull request#116AntoninPoche2026-01-08 14:17
- Issue#115AntoninPoche2025-12-04 18:03`Granularity.SENTENCE` is unpredictable.
- Issue#101thomas-mullor2025-11-20 08:47Casting error with quantized models
- Pull request#104AntoninPoche2025-11-20 08:42
- Issue#100AntoninPoche2025-11-20 08:37AttributionOutput object is not serializable due to staticmethod(lambda) in InferenceModes
- Issue#109NLP-traveller2025-11-06 10:12Excessive size of attribution_output
- Issue#109NLP-traveller2025-11-06 10:12Excessive size of attribution_output
- Issue comment#107AntoninPoche2025-11-03 10:26Compute gradient by perturbation
- Pull request#107ClementBM-CLB2025-10-15 15:20
- Pull request#105thomas-mullor2025-10-08 14:06
- Pull request#104thomas-mullor2025-10-08 12:12
- Pull request#103ClementBM-CLB2025-10-07 15:24
- Pull request#102AntoninPoche2025-10-07 14:24
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 60 stars here means stars gained during the window, not the repo's star count.