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. 3106
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to sports, particularly batting averages and percentages

    oai_token-act-pair · gpt-3.5-turbo

    periods and their associated numerical statistics

    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
     appropri
    -0.75
     welcome
    -0.75
     behalf
    -0.72
     hospitality
    -0.71
     recogn
    -0.71
    rers
    -0.71
    oÄŁ
    -0.70
     undert
    -0.68
     sorely
    -0.68
     recognised
    -0.68
    POSITIVE LOGITS
    NET
    0.95
    -.
    0.94
    _.
    0.93
    gif
    0.91
    ©¶æ¥µ
    0.90
    aspx
    0.88
    300
    0.87
    500
    0.87
    pees
    0.86
    QB
    0.86
    Activations Density 0.019%

    No Known Activations