© 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. 5130
    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
    ra
    -0.11
     by
    -0.08
    _by
    -0.08
    -0.07
     Y
    -0.07
    ord
    -0.06
    len
    -0.06
    (len
    -0.05
     len
    -0.05
    cy
    -0.05
    POSITIVE LOGITS
    rap
    0.12
    ments
    0.09
    's
    0.09
    ]]↵
    0.08
     ny
    0.08
    $
    0.08
    les
    0.08
    ings
    0.08
    ion
    0.07
    red
    0.07
    Activations Density 33.056%

    No Known Activations