© 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. 8-RES-JB
    11. 1979
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Will" or derivatives thereof

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names associated with prominent figures and titles in popular culture

    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
    è¦ļéĨĴ
    -0.79
    netflix
    -0.67
    âĸĵ
    -0.60
    ++++
    -0.59
    姫
    -0.59
    resso
    -0.59
     INC
    -0.57
    anni
    -0.56
    ackets
    -0.56
    cised
    -0.55
    POSITIVE LOGITS
    imus
    0.71
    fulness
    0.69
    FUL
    0.69
    ful
    0.69
     Testament
    0.67
    oso
    0.62
     vo
    0.62
    esome
    0.62
    venge
    0.62
    arge
    0.61
    Activations Density 0.142%

    No Known Activations