© 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. 12884
    Prev
    Next
    INDEX
    Explanations

    HTML/CSS/JavaScript code segments

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotation marks and their usage around different types of content

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    Ļ½
    -0.66
    anship
    -0.64
    facts
    -0.63
    anke
    -0.62
     Flavoring
    -0.61
    jury
    -0.60
    antine
    -0.59
    chwitz
    -0.57
    ordinary
    -0.57
    anova
    -0.57
    POSITIVE LOGITS
     %%
    1.09
     />
    1.01
     href
    0.89
    +(
    0.88
    /"
    0.82
     parsed
    0.78
     alias
    0.77
    >>\
    0.75
     +
    0.74
    ãĤĴ
    0.73
    Activations Density 0.058%

    No Known Activations