© 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. 13380
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gpt-3.5-turbo

    various types of quotation marks and parentheses in code snippets

    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
     buoy
    -0.79
     hardened
    -0.78
     Fisheries
    -0.78
     dogged
    -0.77
     bitters
    -0.76
     intermitt
    -0.75
     pacing
    -0.75
     younger
    -0.75
     creep
    -0.73
     differentiated
    -0.73
    POSITIVE LOGITS
    hello
    1.65
    Hello
    1.57
    SELECT
    1.49
    foo
    1.46
    abc
    1.43
    {"
    1.37
    ../
    1.37
    ./
    1.35
    MpServer
    1.34
    example
    1.33
    Activations Density 0.057%

    No Known Activations