© 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. 14260
    Prev
    Next
    INDEX
    Explanations

    details about famous individuals in various fields such as sports, entertainment, and politics

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals' backgrounds or identities, particularly their nationality, former roles, and achievements

    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
    ipedia
    -0.79
    mbuds
    -0.78
    noon
    -0.71
    fo
    -0.64
     sshd
    -0.63
     Helpful
    -0.62
    nih
    -0.62
    atel
    -0.61
    misc
    -0.60
    idden
    -0.60
    POSITIVE LOGITS
     opted
    0.81
     underwent
    0.79
     survived
    0.76
     joked
    0.76
     effortlessly
    0.75
     endured
    0.74
     duo
    0.74
    stood
    0.73
    hemoth
    0.73
     admits
    0.73
    Activations Density 0.272%

    No Known Activations