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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 2142
    Prev
    Next
    INDEX
    Explanations

    descriptions of actions in a sports match

    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
    381
    +0.11
    0.5%
    238
    +0.10
    0.5%
    433
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.11
    0.09
    533
    +0.10
    0.09
    500
    +0.10
    0.08
    Negative Logits
     Canaver
    -0.86
     curric
    -0.83
    indust
    -0.82
    netflix
    -0.79
    ersive
    -0.79
    chwitz
    -0.78
    enegger
    -0.78
    forums
    -0.77
    onym
    -0.77
     academia
    -0.75
    POSITIVE LOGITS
     scorer
    1.11
     stopp
    1.04
     halftime
    1.04
     teammate
    1.02
     scored
    1.01
     score
    1.01
    tackle
    1.00
     scoring
    0.99
     foul
    0.95
     touchdown
    0.93
    Activations Density 1.917%

    No Known Activations