© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 3198
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    as
    -0.05
    thod
    -0.04
     [↵
    -0.04
    _per
    -0.03
     per
    -0.03
     def
    -0.03
    (con
    -0.03
    per
    -0.03
    (c
    -0.02
     :
    -0.02
    POSITIVE LOGITS
    ))
    0.07
    (min
    0.06
     min
    0.06
    min
    0.06
    _min
    0.05
    max
    0.05
    (max
    0.05
     max
    0.05
    _max
    0.04
    ;
    0.04
    Activations Density 9.398%

    No Known Activations