© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20854
    Prev
    Next
    INDEX
    Explanations

    locations and cities

    oai_token-act-pair · gpt-3.5-turbo

    names of locations and specific geographic entities

    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
    ocratic
    -0.67
    ãĤ±
    -0.67
    geist
    -0.65
     nonex
    -0.63
    phas
    -0.62
    ronic
    -0.56
     lowly
    -0.56
    ãĥĥãĤ¯
    -0.55
    Ö¼
    -0.55
    omorph
    -0.54
    POSITIVE LOGITS
     Photograph
    1.00
     PHOTO
    0.95
     photographed
    0.91
     Copyright
    0.91
     Photographer
    0.90
     Photo
    0.90
    ;;;;;;;;;;;;
    0.86
     celebrates
    0.84
     Courtesy
    0.83
     REUTERS
    0.82
    Activations Density 0.282%

    No Known Activations