© 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. 9-RES-JB
    11. 11474
    Prev
    Next
    INDEX
    Explanations

    instances of the word "toggle."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    toggle captions or descriptions in images and articles

    oai_token-act-pair · gpt-3.5-turbo
    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
    bats
    -0.79
    comed
    -0.68
    dies
    -0.66
    ivism
    -0.65
    dates
    -0.63
    nov
    -0.63
    eday
    -0.63
    naires
    -0.62
     Mata
    -0.61
     Expend
    -0.60
    POSITIVE LOGITS
     caption
    1.24
     toggle
    0.94
     Courtesy
    0.78
    ption
    0.76
     copyright
    0.73
    taboola
    0.66
     {"
    0.66
    ãĤ¤
    0.66
    SpaceEngineers
    0.66
    ãĤ¢
    0.66
    Activations Density 0.007%

    No Known Activations