© 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. 4-RES-JB
    11. 4882
    Prev
    Next
    INDEX
    Explanations

    the name "Brigette" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Brig" or various brigade-related designations

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

    No Comments

    Negative Logits
     Hungarian
    -0.71
     Helsinki
    -0.67
     Gutenberg
    -0.66
     Franken
    -0.64
     Fusion
    -0.64
    onomy
    -0.64
     Gingrich
    -0.62
     Ceres
    -0.61
     Result
    -0.61
     Predators
    -0.60
    POSITIVE LOGITS
    adier
    1.43
     brig
    1.13
    itte
    1.13
    ading
    0.99
    inally
    0.99
    gae
    0.97
    antine
    0.95
    ments
    0.94
    isons
    0.94
    aded
    0.93
    Activations Density 0.011%

    No Known Activations