© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 41607
    Prev
    Next
    INDEX
    Explanations

    the name "Vick" and its variations in context

    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
    288
    +0.13
    0.6%
    314
    +0.13
    0.6%
    718
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.01
    457
    +0.13
    0.01
    536
    +0.11
    0.01
    Negative Logits
     Flavoring
    -0.88
    ppo
    -0.74
    gered
    -0.71
     taxing
    -0.67
     Codec
    -0.65
     beans
    -0.64
     plur
    -0.64
    ãĥ©ãĥ³
    -0.63
    */(
    -0.62
    ======
    -0.61
    POSITIVE LOGITS
    ery
    1.11
    ston
    0.94
    sburgh
    0.85
    erman
    0.84
    igans
    0.83
    istani
    0.82
    rone
    0.82
    enger
    0.82
    lynn
    0.81
    igan
    0.81
    Activations Density 0.003%

    No Known Activations