© 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. 1-RES-JB
    11. 20447
    Prev
    Next
    INDEX
    Explanations

    Full names containing the word "Schultz"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names associated with a significant number of mentions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ãĥ¼ãĥ³
    -0.76
    66666666
    -0.74
    ccording
    -0.73
    orate
    -0.72
     Apollo
    -0.71
     Chatt
    -0.70
    ãģ¦
    -0.69
     Mith
    -0.69
    ãĤ¨ãĥ«
    -0.66
     Gemini
    -0.64
    POSITIVE LOGITS
     Schultz
    1.20
    olicy
    1.09
    ultz
    1.03
    steen
    0.89
    arella
    0.84
    wcs
    0.80
    ratulations
    0.80
    midt
    0.79
    hoff
    0.76
     shuffle
    0.75
    Activations Density 0.003%

    No Known Activations