RRepoGEO

REPOGEO REPORT · LITE

decoderesearch/SAELens

Default branch main · commit 3b3f4cac · scanned 5/24/2026, 11:26:35 PM

GitHub: 1,390 stars · 231 forks

AI VISIBILITY SCORE
28 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 1 warn · 0 fail
Objective metadata checks
AI knows your name
2 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface decoderesearch/SAELens, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • hightopics#1
    Add specific topics for sparse autoencoders and mechanistic interpretability

    Why:

    COPY-PASTE FIX
    sparse-autoencoders, sae, mechanistic-interpretability, ml-interpretability, language-models, deep-learning, pytorch
  • highreadme#2
    Clarify the README's opening sentence to emphasize its core specialization

    Why:

    CURRENT
    # SAE Lens
    COPY-PASTE FIX
    # SAELens: A Comprehensive Library for Training and Analyzing Sparse Autoencoders in Language Models
  • mediumreadme#3
    Add a 'Why SAELens?' section to highlight its unique value proposition

    Why:

    COPY-PASTE FIX
    ## Why SAELens?

SAELens provides a specialized, comprehensive toolkit for both training and, crucially, *analyzing* sparse autoencoders (SAEs) within language models. While other libraries like TransformerLens, Hugging Face Transformers, or PyTorch offer foundational model capabilities, SAELens focuses specifically on the lifecycle of SAEs, from efficient training to deep mechanistic interpretability and feature visualization. It integrates seamlessly with these frameworks, offering dedicated tools for understanding the internal workings of SAEs that general-purpose libraries do not.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface decoderesearch/SAELens
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
pytorch/captum
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. pytorch/captum · recommended 2×
  2. neelnanda-io/TransformerLens · recommended 1×
  3. Anthropic/sae-training-library · recommended 1×
  4. huggingface/transformers · recommended 1×
  5. pytorch/pytorch · recommended 1×
  • CATEGORY QUERY
    How to train sparse autoencoders for mechanistic interpretability in large language models?
    you: not recommended
    AI recommended (in order):
    1. TransformerLens (neelnanda-io/TransformerLens)
    2. SAE-Training-Library (Anthropic/sae-training-library)
    3. Hugging Face Transformers (huggingface/transformers)
    4. PyTorch (pytorch/pytorch)
    5. JAX (google/jax)
    6. TensorFlow (tensorflow/tensorflow)
    7. Captum (pytorch/captum)
    8. Interpret-LM

    AI recommended 8 alternatives but never named decoderesearch/SAELens. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What tools help analyze sparse autoencoder features to understand neural network behavior?
    you: not recommended
    AI recommended (in order):
    1. TensorBoard (tensorflow/tensorboard)
    2. UMAP (lmcinnes/umap)
    3. Captum (pytorch/captum)
    4. SHAP (shap/shap)
    5. Lucid (tensorflow/lucid)
    6. Netron (lutzroeder/netron)
    7. DeepView.js (deepviewjs/deepview.js)

    AI recommended 7 alternatives but never named decoderesearch/SAELens. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    warn

    Suggestion:

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of decoderesearch/SAELens?
    pass
    AI named decoderesearch/SAELens explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts decoderesearch/SAELens in production, what risks or prerequisites should they evaluate first?
    pass
    AI named decoderesearch/SAELens explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo decoderesearch/SAELens solve, and who is the primary audience?
    pass
    AI did not name decoderesearch/SAELens — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of decoderesearch/SAELens. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/decoderesearch/SAELens.svg)](https://repogeo.com/en/r/decoderesearch/SAELens)
HTML
<a href="https://repogeo.com/en/r/decoderesearch/SAELens"><img src="https://repogeo.com/badge/decoderesearch/SAELens.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

decoderesearch/SAELens — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite