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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 4160
    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
    ser
    -0.09
     _
    -0.09
    =
    -0.07
    isit
    -0.05
    verage
    -0.05
    asks
    -0.05
    distan
    -0.05
    alue
    -0.05
    arest
    -0.05
    irst
    -0.04
    POSITIVE LOGITS
    ;
    0.13
    dint
    0.08
    (),
    0.08
     **
    0.08
     {↵
    0.06
    &
    0.06
    $
    0.06
    .get
    0.05
    }:
    0.04
     sele
    0.04
    Activations Density 73.880%

    No Known Activations