© 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. 10323
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations, specifically the city of Cairo

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations or terms associated with specific places

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     respons
    -0.72
    govtrack
    -0.64
    esville
    -0.63
     resemb
    -0.62
     dread
    -0.61
    borne
    -0.61
    sterdam
    -0.61
    myra
    -0.59
    shire
    -0.59
    vana
    -0.59
    POSITIVE LOGITS
    urnal
    0.78
    uner
    0.77
    ococ
    0.74
    chuk
    0.73
    âĸ¬
    0.73
    âĸ¬âĸ¬
    0.69
    ukong
    0.66
    aku
    0.64
    æ©
    0.64
    henko
    0.63
    Activations Density 0.208%

    No Known Activations