© 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. 7-RES-JB
    11. 9881
    Prev
    Next
    INDEX
    Explanations

    names specifically "Shawn" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Shawn."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hiba
    -0.82
     fitting
    -0.73
    gers
    -0.70
    andom
    -0.69
    gered
    -0.67
    âĶĢâĶĢ
    -0.66
    QUI
    -0.65
    keley
    -0.65
    è¡
    -0.65
    scill
    -0.65
    POSITIVE LOGITS
    sylvania
    1.04
    eer
    0.89
    ees
    0.86
    sburg
    0.86
    ee
    0.84
     Michaels
    0.83
    arya
    0.83
    iard
    0.82
    naire
    0.80
    een
    0.79
    Activations Density 0.055%

    No Known Activations