© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 20817
    Prev
    Next
    INDEX
    Explanations

    functions and declarations in a programming context

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to programming and class definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    advertising
    -0.89
    agall
    -0.86
    conservancy
    -0.85
    omen
    -0.80
    ¨
    -0.80
    stood
    -0.76
    yet
    -0.76
    Ward
    -0.76
    soType
    -0.75
    .–
    -0.74
    POSITIVE LOGITS
     foo
    1.01
     Main
    0.99
     Foo
    0.96
     main
    0.95
     initialize
    0.95
     __
    0.94
     hello
    0.89
     Default
    0.86
     Config
    0.85
     My
    0.83
    Activations Density 0.047%

    No Known Activations