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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 7178
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific video game series

    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
    635
    +0.16
    0.7%
    211
    +0.11
    0.5%
    218
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.16
    0.03
    326
    +0.11
    0.03
    343
    +0.11
    0.02
    Negative Logits
    lla
    -0.81
     Emin
    -0.78
    sson
    -0.78
    edly
    -0.78
    hands
    -0.73
    iferation
    -0.70
    enegger
    -0.70
    bridge
    -0.70
    vich
    -0.69
    cens
    -0.68
    POSITIVE LOGITS
     Haram
    0.94
    unin
    0.81
    assian
    0.80
    ça
    0.77
    ét
    0.77
    unta
    0.73
    upid
    0.69
    ilee
    0.69
    otic
    0.66
    ģĸ
    0.66
    Activations Density 0.083%

    No Known Activations