© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7489
    Prev
    Next
    INDEX
    Explanations

    the names or words containing "uy"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "Huy" and its derivatives, along with other names and terms

    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
    NetMessage
    -0.75
    Downloadha
    -0.73
    ngth
    -0.73
    milo
    -0.71
    essional
    -0.68
    elaide
    -0.67
    iership
    -0.66
    ciating
    -0.64
    heading
    -0.63
    女
    -0.63
    POSITIVE LOGITS
    aku
    0.99
    uki
    0.92
    uy
    0.90
    outube
    0.87
    ãĤ¡
    0.87
    utsu
    0.85
    BLIC
    0.81
    gments
    0.81
    uko
    0.79
    rue
    0.78
    Activations Density 0.014%

    No Known Activations