© 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. 20974
    Prev
    Next
    INDEX
    Explanations

    numerical values in a specific format, often appearing as percentages or decimal numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistical data

    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
    urat
    -0.74
     overt
    -0.61
     divest
    -0.61
    hetti
    -0.59
     realistically
    -0.59
    pocket
    -0.58
     severed
    -0.58
     youth
    -0.57
     consecut
    -0.57
    ively
    -0.57
    POSITIVE LOGITS
    GHz
    1.08
     GHz
    0.94
    BSD
    0.91
    ©¶æ¥µ
    0.90
     oz
    0.87
    %:
    0.86
    MB
    0.86
     Ranked
    0.85
    %"
    0.85
    %
    0.84
    Activations Density 0.037%

    No Known Activations