© 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. 8-RES-JB
    11. 14134
    Prev
    Next
    INDEX
    Explanations

    words related to awards, recognition, and achievements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to players of the year and their awards in sports

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    duino
    -0.79
    enegger
    -0.71
    ondon
    -0.71
    agen
    -0.69
     Alz
    -0.68
    kinson
    -0.67
    ements
    -0.67
    ittal
    -0.65
    isure
    -0.65
    yg
    -0.65
    POSITIVE LOGITS
     contender
    1.10
     honors
    1.02
     awards
    0.95
     Award
    0.95
     award
    0.94
     accol
    0.90
     Awards
    0.87
    Winner
    0.86
     contenders
    0.86
     finalists
    0.83
    Activations Density 0.066%

    No Known Activations