© 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. 11160
    Prev
    Next
    INDEX
    Explanations

    commands or prompts for an action from the user

    oai_token-act-pair · gpt-3.5-turbo

    calls to action and engagement prompts

    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
    TEXTURE
    -0.61
    rolet
    -0.57
    ovember
    -0.57
    ffer
    -0.56
    rist
    -0.54
    appa
    -0.54
    uras
    -0.53
    uder
    -0.53
    ARY
    -0.52
    rador
    -0.52
    POSITIVE LOGITS
     Cancel
    0.77
    ONSORED
    0.73
    cknow
    0.61
     Oops
    0.57
     Seat
    0.56
    anie
    0.54
     Sample
    0.51
    APD
    0.51
    icans
    0.51
     Error
    0.50
    Activations Density 0.143%

    No Known Activations