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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 4873
    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
    _
    -0.11
    ._
    -0.08
    inal
    -0.08
    rite
    -0.07
    (),
    -0.06
     defaultdict
    -0.06
    di
    -0.06
    der
    -0.05
     obstac
    -0.05
    a
    -0.05
    POSITIVE LOGITS
    ulate
    0.08
    um
    0.08
    ulation
    0.07
    ross
    0.07
    ul
    0.07
    udok
    0.07
    lauses
    0.06
    dom
    0.06
    The
    0.05
    udoku
    0.05
    Activations Density 56.617%

    No Known Activations