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 · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 239
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data in written content

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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

    Neuron Alignment
    Index
    Value
    % of L₁
    488
    +0.10
    0.4%
    552
    +0.09
    0.4%
    89
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    149
    +0.10
    0.07
    283
    +0.09
    0.03
    739
    +0.09
    0.04
    Negative Logits
     nurture
    -0.78
    ²¾
    -0.70
    NetMessage
    -0.69
     proactive
    -0.69
     earnest
    -0.68
     nurturing
    -0.66
     interaction
    -0.66
    olitical
    -0.66
     DRM
    -0.65
    vertisements
    -0.65
    POSITIVE LOGITS
    total
    1.10
     averages
    1.02
    Percent
    1.00
     compared
    1.00
    average
    0.99
    maximum
    0.98
     total
    0.97
    Total
    0.97
     averaged
    0.94
    Maximum
    0.91
    Activations Density 3.489%

    No Known Activations