© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1417
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "oku" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    the term "oku" in various contexts, particularly related to historical or cultural figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     casualty
    -0.66
     ev
    -0.64
     observer
    -0.64
     Hem
    -0.64
     Photograph
    -0.63
     Charlottesville
    -0.63
     indirect
    -0.63
     incidental
    -0.63
     Cyn
    -0.62
     liaison
    -0.61
    POSITIVE LOGITS
    oku
    4.94
    aku
    1.45
    inki
    1.18
    imaru
    1.16
    eki
    1.16
    ahime
    1.16
    oka
    1.15
    uki
    1.15
    etsu
    1.14
    odo
    1.12
    Activations Density 0.007%

    No Known Activations