© 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. 6979
    Prev
    Next
    INDEX
    Explanations

    words related to the Star Wars planet Hoth

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or references related to the "Goth" style or culture

    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
     Kislyak
    -0.69
    assetsadobe
    -0.68
     Waterloo
    -0.67
    verett
    -0.65
    GMT
    -0.63
     Wiggins
    -0.62
     Hutchinson
    -0.62
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
    yip
    -0.61
    ETS
    -0.61
    POSITIVE LOGITS
    ouse
    0.88
    orse
    0.82
    aus
    0.80
    oth
    0.80
    fold
    0.78
    iop
    0.78
    face
    0.78
    child
    0.77
    shire
    0.76
    oths
    0.75
    Activations Density 0.012%

    No Known Activations