© 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. 12-RES-JB
    11. 2473
    Prev
    Next
    INDEX
    Explanations

    words related to competition, leadership, and political events

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    terms related to leads, advantages, and positioning in competitive contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    mbuds
    -0.73
    ij士
    -0.69
     millenn
    -0.67
     opio
    -0.67
    wagen
    -0.66
    obyl
    -0.65
     acron
    -0.62
    Balt
    -0.61
     welf
    -0.60
     Pengu
    -0.60
    POSITIVE LOGITS
     heading
    1.12
     advantage
    1.07
     against
    1.05
     over
    0.94
     atop
    0.93
     nationally
    0.88
     versus
    0.87
     among
    0.85
    holding
    0.83
     ahead
    0.81
    Activations Density 0.104%

    No Known Activations