Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 16550
    Prev
    Next
    INDEX
    Explanations

    names of Japanese individuals, especially those related to the entertainment industry

    oai_token-act-pair · gpt-3.5-turbo

    the names of Japanese creators, specifically those associated with the video game and animation industries

    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
    elaide
    -0.74
     trooper
    -0.70
    sylvania
    -0.70
     Commonwealth
    -0.69
     Scotia
    -0.69
    Ħ¢
    -0.68
     Vaugh
    -0.66
    ICE
    -0.65
     Rebels
    -0.65
     Solitaire
    -0.64
    POSITIVE LOGITS
    amoto
    1.46
    azaki
    1.42
    asaki
    1.31
    ikawa
    1.29
    imura
    1.29
    oka
    1.25
    ihara
    1.20
    aido
    1.18
    imoto
    1.16
    atsu
    1.14
    Activations Density 0.071%

    No Known Activations