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 3072
    5. 8-RES_FS3072-JB
    6. 612
    Prev
    Next
    INDEX
    Explanations

    text related to sports statistics and analysis

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    184
    +0.10
    0.5%
    293
    +0.09
    0.4%
    412
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.10
    0.06
    570
    +0.09
    0.02
    648
    +0.09
    0.07
    Negative Logits
    bard
    -0.72
    hement
    -0.70
    western
    -0.69
    ©¶æ
    -0.67
    minist
    -0.66
    nik
    -0.66
    older
    -0.65
    ĪĴ
    -0.65
    gently
    -0.65
    artisan
    -0.64
    POSITIVE LOGITS
     percentage
    1.27
     total
    1.21
     calories
    1.14
     GDP
    1.13
     Calories
    1.13
     mileage
    1.05
     number
    1.04
     Percentage
    1.04
    total
    1.02
     per
    1.01
    Activations Density 1.884%

    No Known Activations