© 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. 7842
    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
     __
    -0.07
    ¹
    -0.03
    d
    -0.03
    ump
    -0.03
    and
    -0.03
     heuristic
    -0.02
    uristic
    -0.02
    da
    -0.02
    _and
    -0.02
    oal
    -0.02
    POSITIVE LOGITS
     representing
    0.08
    air
    0.06
    ]][
    0.06
    sions
    0.05
     that
    0.05
     given
    0.05
    ir
    0.05
    ake
    0.05
     each
    0.05
     the
    0.05
    Activations Density 46.616%

    No Known Activations