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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 43420
    Prev
    Next
    INDEX
    Explanations

    references to the Carolina Panthers football team

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    484
    +0.15
    0.7%
    453
    +0.11
    0.5%
    383
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.15
    0.01
    388
    +0.11
    0.01
    648
    +0.10
    0.01
    Negative Logits
    edited
    -0.69
    iannopoulos
    -0.67
    quickShipAvailable
    -0.67
    ngth
    -0.67
     quot
    -0.65
    DonaldTrump
    -0.65
    between
    -0.64
    ploma
    -0.64
    dit
    -0.63
     Pradesh
    -0.62
    POSITIVE LOGITS
     Panther
    0.99
     Panthers
    0.90
     Hurricanes
    0.79
     Coliseum
    0.77
    sburg
    0.71
     Saints
    0.67
    sburgh
    0.67
    ville
    0.66
    ulla
    0.66
    piracy
    0.66
    Activations Density 0.002%

    No Known Activations