© 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 12288
    9. 8-RES_FS12288-JB
    11. 9863
    Prev
    Next
    INDEX
    Explanations

    keywords related to gaming, such as game titles, game mechanics, and terms commonly used in gaming contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    459
    +0.11
    0.5%
    544
    +0.09
    0.4%
    621
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.11
    0.05
    683
    +0.09
    0.05
    659
    +0.09
    0.05
    Negative Logits
    "},"
    -0.73
     attm
    -0.64
     Grateful
    -0.61
     Mehran
    -0.60
     Shutterstock
    -0.60
     ancest
    -0.59
     eternity
    -0.58
     UID
    -0.58
     Canaver
    -0.57
     Wasserman
    -0.55
    POSITIVE LOGITS
     likewise
    1.05
     meanwhile
    1.01
     similarly
    0.83
     fared
    0.79
    aurus
    0.79
    itto
    0.78
     Chaser
    0.69
     gave
    0.68
    another
    0.66
    oother
    0.66
    Activations Density 0.703%

    No Known Activations