© 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 EvalsExportsAPI 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. 10-RES-JB
    11. 6190
    Prev
    Next
    INDEX
    Explanations

    locations or references related to the city of São Paulo, Brazil

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of São Paulo and related terms or concepts associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lot
    -0.74
    Ö¼
    -0.72
    creen
    -0.71
    baugh
    -0.69
    ewski
    -0.68
    mable
    -0.67
    omsky
    -0.66
    rals
    -0.66
    rons
    -0.66
    mel
    -0.66
    POSITIVE LOGITS
     Paulo
    1.37
    qi
    0.98
    ÄŁ
    0.95
    vernment
    0.92
     Mata
    0.90
    zzi
    0.89
     Tome
    0.86
     Sao
    0.86
     Zed
    0.83
    pport
    0.83
    Activations Density 0.067%

    No Known Activations