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. 10-RES-JB
    6. 19368
    Prev
    Next
    INDEX
    Explanations

    references to publications and releases of manga, anime, and related media

    oai_token-act-pair · gpt-3.5-turbo

    information about upcoming manga and anime releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maxwell
    -0.95
     Rockefeller
    -0.94
    cair
    -0.91
     Carson
    -0.88
     Stoke
    -0.86
     Mason
    -0.85
     Roose
    -0.84
     Watkins
    -0.83
     Brigham
    -0.83
     Howe
    -0.82
    POSITIVE LOGITS
     manga
    1.67
     anime
    1.57
     Anime
    1.42
     Manga
    1.37
     ãĤ
    1.24
     ãĥ
    1.21
    Japanese
    1.20
     ãĢĮ
    1.16
     ¥
    1.15
    ãĢİ
    1.14
    Activations Density 0.372%

    No Known Activations