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. 581
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions for recipes

    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
    524
    +0.12
    0.5%
    228
    +0.11
    0.5%
    545
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    390
    +0.12
    0.06
    545
    +0.11
    0.07
    524
    +0.10
    0.07
    Negative Logits
    ¥µ
    -0.89
    assetsadobe
    -0.77
    fm
    -0.75
    idays
    -0.74
     tours
    -0.70
    omsday
    -0.70
    detail
    -0.70
    iors
    -0.69
    2019
    -0.68
    aday
    -0.67
    POSITIVE LOGITS
     cloves
    1.05
     tsp
    1.04
     garlic
    1.01
     cinnamon
    0.99
    poons
    0.98
     diced
    0.98
     pinch
    0.97
     yeast
    0.97
     minced
    0.96
     ½
    0.94
    Activations Density 0.935%

    No Known Activations