© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 16086
    Prev
    Next
    INDEX
    Explanations

    functions and definitions in a programming context

    oai_token-act-pair · gpt-3.5-turbo

    function and class declarations in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ¦)
    -0.80
    soDeliveryDate
    -0.78
    agall
    -0.76
    ukong
    -0.73
    ë
    -0.72
    externalActionCode
    -0.72
    Magikarp
    -0.70
    76561
    -0.70
    soType
    -0.70
    DK
    -0.68
    POSITIVE LOGITS
     __
    0.96
     initialize
    0.83
     main
    0.79
     init
    0.77
     _
    0.77
     Main
    0.77
     foo
    0.76
     Shutdown
    0.74
     Activate
    0.73
    \\\\\\\\\\\\\\\\
    0.69
    Activations Density 0.044%

    No Known Activations