© 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. 6-RES-JB
    11. 7926
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals, potentially celebrities or public figures

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of names and proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå¥ij士
    -0.69
    »Ĵ
    -0.67
    ãģ¦
    -0.67
     bluff
    -0.67
    Effective
    -0.66
     cellul
    -0.66
     DRAG
    -0.62
     stewards
    -0.62
     apology
    -0.59
     Flavoring
    -0.59
    POSITIVE LOGITS
    andro
    0.79
    ocene
    0.77
    orce
    0.73
    frog
    0.73
    ograp
    0.72
    velt
    0.72
    itte
    0.72
    igne
    0.71
    este
    0.71
     qui
    0.71
    Activations Density 0.068%

    No Known Activations