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

    Neuronpedia

    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. 10030
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical information

    oai_token-act-pair · gpt-3.5-turbo

    special characters, numbers, and formatting indicators typically seen in structured data or 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
    yip
    -0.96
    ĺħ
    -0.83
    xon
    -0.78
    tsky
    -0.67
    ospace
    -0.63
    idth
    -0.63
    aturdays
    -0.63
     fold
    -0.63
    ngth
    -0.62
    hesda
    -0.61
    POSITIVE LOGITS
    ":{"
    1.02
    ":[{"
    0.96
    ãĥĻ
    0.93
    ":["
    0.92
    Buyable
    0.91
    ":"
    0.89
    channelAvailability
    0.87
    ":[
    0.85
    ?????-
    0.80
    ä
    0.80
    Activations Density 0.100%

    No Known Activations