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. 43355
    Prev
    Next
    INDEX
    Explanations

    words related to alcoholic beverages and parties

    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
    88
    +0.11
    0.5%
    316
    +0.11
    0.5%
    2
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.01
    659
    +0.11
    0.01
    316
    +0.10
    0.01
    Negative Logits
    iversal
    -0.86
    aido
    -0.82
    DAY
    -0.81
    nesota
    -0.80
    orate
    -0.78
    İĭ
    -0.78
    emade
    -0.77
    orable
    -0.77
    omo
    -0.77
     srf
    -0.76
    POSITIVE LOGITS
    aux
    1.14
    lli
    1.08
    llo
    0.95
    lla
    0.93
    ux
    0.80
    bourg
    0.79
    urs
    0.78
    agne
    0.78
     du
    0.78
     Hollande
    0.76
    Activations Density 0.009%

    No Known Activations