© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 7918
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ak
    -0.02
    .write
    -0.01
    %
    -0.01
    hest
    -0.01
    __
    -0.01
    '
    0.00
    #
    0.00
    &
    0.00
    *
    0.00
    )
    0.00
    POSITIVE LOGITS
    param
    0.13
    args
    0.12
    arg
    0.09
     Par
    0.08
     par
    0.08
    _par
    0.07
    par
    0.06
    .add
    0.04
     command
    0.04
    ė
    0.04
    Activations Density 3.992%

    No Known Activations