© 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. 10-RES-JB
    11. 18792
    Prev
    Next
    INDEX
    Explanations

    requests for verification to confirm that someone is not a robot

    oai_token-act-pair · gpt-3.5-turbo

    phrases concerning user verification and registration processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    blow
    -0.57
    igans
    -0.56
     laps
    -0.56
    BuyableInstoreAndOnline
    -0.55
     adv
    -0.55
     ostr
    -0.54
     gal
    -0.54
     unaccount
    -0.54
    pport
    -0.53
     Canaver
    -0.53
    POSITIVE LOGITS
    're
    0.74
    urrency
    0.72
    ve
    0.70
    iframe
    0.67
    user
    0.63
    worthiness
    0.63
    uncture
    0.63
    claimer
    0.63
     Sign
    0.63
    cmp
    0.61
    Activations Density 0.019%

    No Known Activations