© 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. 11-RES-JB
    11. 7882
    Prev
    Next
    INDEX
    Explanations

    hyperlinks or calls to action indicated by the text "Click here."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "click here" or similar calls to action for further engagement

    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
    anking
    -0.62
    oké
    -0.61
    bent
    -0.57
     effected
    -0.56
    awed
    -0.56
    Ö¼
    -0.55
    nesota
    -0.55
    etheless
    -0.54
    cade
    -0.54
    offensive
    -0.52
    POSITIVE LOGITS
     Oops
    0.95
     for
    0.76
    >>
    0.76
     to
    0.76
     âĨĴ
    0.73
     if
    0.71
     Subscribe
    0.71
     NEXT
    0.70
     thumbnail
    0.68
    umbnail
    0.68
    Activations Density 0.061%

    No Known Activations