© 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. 11-RES-JB
    11. 7579
    Prev
    Next
    INDEX
    Explanations

    the name "Taylor Swift"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Taylor" and "Taylor Swift."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hemy
    -0.83
    pread
    -0.77
    ser
    -0.77
    oard
    -0.75
    sets
    -0.72
    rely
    -0.70
    sky
    -0.69
    onent
    -0.68
    cffffcc
    -0.67
    rated
    -0.66
    POSITIVE LOGITS
     Swift
    1.18
    Made
    1.05
    ©¶æ¥µ
    0.76
     Beckham
    0.73
    @#&
    0.73
    Joy
    0.72
     Hawkins
    0.71
     Kemp
    0.68
    edo
    0.68
     Powers
    0.66
    Activations Density 0.038%

    No Known Activations