© 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. 8-RES-JB
    11. 10520
    Prev
    Next
    INDEX
    Explanations

    the word "Khan"

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the name "Khan."

    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
    iculty
    -0.68
    perature
    -0.67
    ezvous
    -0.64
    ources
    -0.62
    ensical
    -0.62
     myster
    -0.61
    PORT
    -0.60
    cedes
    -0.57
    ciples
    -0.57
    erence
    -0.56
    POSITIVE LOGITS
    istani
    1.04
     Sheikh
    0.91
    mare
    0.86
     Noon
    0.86
    abal
    0.85
    adesh
    0.83
    allah
    0.81
     Khan
    0.79
    wal
    0.79
    uddin
    0.79
    Activations Density 0.038%

    No Known Activations