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. 43431
    Prev
    Next
    INDEX
    Explanations

    references to the holiday of Christmas

    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
    421
    +0.13
    0.6%
    288
    +0.13
    0.6%
    459
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    141
    +0.13
    0.02
    421
    +0.13
    0.02
    214
    +0.12
    0.02
    Negative Logits
    auga
    -0.76
     constitu
    -0.75
    chnology
    -0.71
    ector
    -0.70
    umbn
    -0.69
     fluoride
    -0.68
    restling
    -0.68
    VICE
    -0.67
    agonist
    -0.67
    SPONSORED
    -0.67
    POSITIVE LOGITS
     Eve
    1.24
     eve
    0.95
     holidays
    0.90
     Day
    0.89
     Island
    0.88
     Tree
    0.86
     Carol
    0.85
     Claus
    0.81
     decorations
    0.78
     Surprise
    0.76
    Activations Density 0.016%

    No Known Activations