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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8078
    Prev
    Next
    INDEX
    Explanations

    references to crowdfunding platforms

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific crowdfunding platform

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.90
    ioned
    -0.83
    ĸļ
    -0.78
    âĢ¢âĢ¢
    -0.70
     Shutterstock
    -0.66
    =-=-=-=-
    -0.66
    aeda
    -0.65
    cens
    -0.65
    rawdownloadcloneembedreportprint
    -0.65
    xon
    -0.64
    POSITIVE LOGITS
    fried
    1.04
    ieg
    0.91
    ennes
    0.89
    ert
    0.83
    raphics
    0.81
    ogo
    0.81
    iew
    0.77
    ener
    0.77
    agements
    0.77
    vernment
    0.75
    Activations Density 0.017%

    No Known Activations