© 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. 8-RES-JB
    11. 20380
    Prev
    Next
    INDEX
    Explanations

    phrases related to the United States of America

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "America"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStreamFrame
    -0.75
    heed
    -0.75
    NB
    -0.74
    enser
    -0.63
    ijk
    -0.63
    TY
    -0.63
    operation
    -0.62
    orders
    -0.62
     annotation
    -0.62
    isson
    -0.62
    POSITIVE LOGITS
     Airlines
    0.96
    ICAN
    0.94
     Idol
    0.90
     Mov
    0.85
     Samoa
    0.83
    icans
    0.77
    èĪ
    0.76
     Skies
    0.75
    's
    0.73
    istar
    0.73
    Activations Density 0.059%

    No Known Activations