Subtext

To know what models don't say out loud.

ninjahawk/Subtext

View on GitHub ↗

To know what models don't say out loud.

Subtext grew +1.6% in the last 30 days, ranks 45th of 80 in Interpretability & Alignment, last commit 121 days ago.

Star trajectory

82 days tracked
2026-08-31250 stars today2026-11-22
Momentum

+1.6% in 30d, above the Interpretability & Alignment median of +0.4%.

Maintenance

Last commit 121 days ago, fresher than the median of 183d.

How it compares in Interpretability & Alignment

Subtext
250
stars
+1.6% 30d
commit 121 days ago
Interpretability & Alignment median
290
stars
+0.4% 30d
commit ~183d ago
Leader · lmms-eval
4.5k
stars
+0.9% 30d
commit today

Ranked 45th of 80 by stars.

Ranked by shared tags, then keywords, then stars
  1. The purpose of this repository is to make prototypes as case study in the context of proof of concept(PoC) and…

    +0 (+0.0%) in 30d · Committed 1,062d ago · Python · GPL-2.0

    Shares Interpretability & Alignment

  2. Benchmarking LLMs via Uncertainty Quantification

    +0 (+0.0%) in 30d · Committed 1,027d ago · Python · MIT

    Shares Interpretability & Alignment

  3. I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by…

    +2 (+0.8%) in 30d · Committed 247d ago · Python

    Shares Interpretability & Alignment

  4. Pivotal Token Search

    +8 (+5.0%) in 30d · Committed 14d ago · Python · Apache-2.0

    Shares Interpretability & Alignment

  5. A Mechanistic Interpretability Toolkit for Cross-Layer Transcoder Training and Attribution-Graph Visualization

    +4 (+3.7%) in 30d · Committed 114d ago · Python · MIT

    Shares Interpretability & Alignment

  6. Official implementation of MemChain for interpretable memory reasoning in memory-augmented LLMs.

    -1 (-1.1%) in 30d · Committed 144d ago · Python · MIT

    Shares Interpretability & Alignment

  7. A JAX research toolkit for building, editing, and visualizing neural networks.

    -2 (-0.1%) in 30d · Committed 518d ago · Python · Apache-2.0

    Shares Interpretability & Alignment

  8. Observe how memory shapes an answer. Pensieve is an interactive system for visualizing, interpreting, and…

    -6 (-0.5%) in 30d · Committed 66d ago · TypeScript · MIT

    Shares Interpretability & Alignment

  9. A small, fast decision model, or system one model, for agentic workflows. Pick between options or rate on a…

    +550 (+79%) in 30d · Committed yesterday · Python · Apache-2.0

    Shares Interpretability & Alignment

  10. A next-generation automatic algorithm design platform, making automated algorithm design more accessible and…

    +49 (+7.3%) in 30d · Committed today · Python · BSD-3-Clause

    Shares Interpretability & Alignment

Language
HTML
License
Other
Contributors
3
Forks
25
Watchers
2
Open issues
0
Releases
0
Created
2026-07-06
Stars this week
+2

You've seen where Subtext stands today.

Get the moves before everyone else: the 5 Interpretability & Alignment repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain Subtext?

Claim this page to add your own call-to-action.

Claim this page