© 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. 9-RES-JB
    11. 10213
    Prev
    Next
    INDEX
    Explanations

    names of individuals holding high-ranking positions in organizations

    oai_token-act-pair · gpt-3.5-turbo

    executive titles and roles in organizations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    zees
    -0.77
    yip
    -0.76
    etitive
    -0.73
    utic
    -0.73
    ophobia
    -0.72
    hazard
    -0.72
    ilitary
    -0.71
    antics
    -0.70
    urgy
    -0.69
    nces
    -0.69
    POSITIVE LOGITS
     CEO
    1.30
     chief
    1.19
    CEO
    1.17
     propriet
    1.09
     chairman
    1.04
     editor
    1.02
     founder
    1.02
     publisher
    1.01
     administrator
    1.01
     namesake
    1.00
    Activations Density 0.062%

    No Known Activations