© 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. 19078
    Prev
    Next
    INDEX
    Explanations

    HTML tags for closing elements, such as "</div>"

    oai_token-act-pair · gpt-3.5-turbo

    HTML and markup language elements

    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
     virginity
    -0.69
    76561
    -0.67
     wrongly
    -0.67
     coinc
    -0.63
     Telesc
    -0.62
     chlorine
    -0.62
     unsuccessfully
    -0.60
     inaccur
    -0.59
     underest
    -0.59
     betrayal
    -0.58
    POSITIVE LOGITS
     html
    0.92
    script
    0.91
    Output
    0.88
    template
    0.87
    HTML
    0.84
    endif
    0.84
     jQuery
    0.79
    CSS
    0.78
    function
    0.77
    Widget
    0.77
    Activations Density 0.053%

    No Known Activations