© 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. 11-RES-JB
    11. 12955
    Prev
    Next
    INDEX
    Explanations

    places and cities with a specific focus on New York, London, Seattle, Gainesville, Manchester, Silicon Valley, Detroit, and Dubai

    oai_token-act-pair · gpt-3.5-turbo

    names of cities and geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ongyang
    -0.68
    lihood
    -0.68
     disputed
    -0.65
    inventory
    -0.65
    orders
    -0.64
    colo
    -0.63
    vol
    -0.63
    administ
    -0.62
    ptoms
    -0.61
    Leod
    -0.61
    POSITIVE LOGITS
     natives
    1.18
     Nights
    1.17
     skyline
    1.06
     accents
    0.96
     accent
    0.94
    ese
    0.93
     Comic
    0.91
    ESE
    0.91
     winters
    0.90
     Calling
    0.88
    Activations Density 0.319%

    No Known Activations