© 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. 7-RES-JB
    11. 18711
    Prev
    Next
    INDEX
    Explanations

    information related to the United States military

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the United States (U.S.) and its government entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bably
    -0.91
    ebook
    -0.77
    igs
    -0.75
    ients
    -0.73
    criptions
    -0.71
    storms
    -0.69
    lets
    -0.68
    oots
    -0.67
    byss
    -0.65
    ãĥł
    -0.65
    POSITIVE LOGITS
     Postal
    1.21
     Embassy
    1.09
     Geological
    1.04
     Navy
    1.01
     Senate
    0.97
     Army
    0.96
     Citizenship
    0.95
     Department
    0.94
     Treasury
    0.93
     Naval
    0.92
    Activations Density 0.083%

    No Known Activations