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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 13370
    Prev
    Next
    INDEX
    Explanations

    percentage values or rates related to success, discount, profit, prevalence, sales growth, occupancy, chance, level, reduction, turnout, variance, turnout or risk

    oai_token-act-pair · gpt-3.5-turbo

    statistics and numerical data related to success and performance rates

    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
    devices
    -0.79
    etheus
    -0.71
    undreds
    -0.71
     itiner
    -0.62
     thousands
    -0.62
    pecially
    -0.62
     Instruments
    -0.61
    cules
    -0.61
    ç«
    -0.60
     innumerable
    -0.60
    POSITIVE LOGITS
     rate
    1.02
     ratio
    0.98
     variance
    0.90
     apiece
    0.89
     compared
    0.88
    %,
    0.87
     respectively
    0.85
     margin
    0.85
     Rate
    0.84
    Percent
    0.83
    Activations Density 0.177%

    No Known Activations