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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11177
    Prev
    Next
    INDEX
    Explanations

    references to sports leagues, particularly the Champions League

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    288
    +0.16
    0.7%
    116
    +0.12
    0.6%
    742
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    116
    +0.16
    0.01
    376
    +0.12
    0.01
    194
    +0.12
    0.01
    Negative Logits
    nu
    -0.80
    packing
    -0.80
    orders
    -0.77
    eral
    -0.75
    tracks
    -0.72
    ering
    -0.72
     Canaver
    -0.72
    shore
    -0.71
    ted
    -0.70
    cffffcc
    -0.70
    POSITIVE LOGITS
     League
    1.30
     Trophy
    1.09
    League
    1.03
     Cup
    0.94
    hip
    0.91
     XI
    0.86
     league
    0.83
     Champions
    0.82
    inia
    0.76
     Cups
    0.76
    Activations Density 0.015%

    No Known Activations