© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 11210
    Prev
    Next
    INDEX
    Explanations

    information or instructions related to enabling JavaScript on a webpage

    oai_token-act-pair · gpt-3.5-turbo

    references to enabling JavaScript and viewing multimedia content

    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
    terday
    -0.78
     Kinnikuman
    -0.64
    olated
    -0.63
    boys
    -0.57
    archives
    -0.57
    olation
    -0.55
    going
    -0.54
    sein
    -0.53
     vanishing
    -0.52
    many
    -0.52
    POSITIVE LOGITS
    qus
    0.88
    embed
    0.83
     Javascript
    0.77
    iframe
    0.69
     javascript
    0.69
     watch
    0.65
     embed
    0.63
    rame
    0.62
    redd
    0.58
     JavaScript
    0.57
    Activations Density 0.026%

    No Known Activations