© 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 768
    9. 8-RES_FS768-JB
    11. 693
    Prev
    Next
    INDEX
    Explanations

    terms related to gaming and game development

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    651
    +0.12
    0.6%
    698
    +0.12
    0.5%
    495
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.12
    0.18
    288
    +0.12
    0.21
    575
    +0.12
    0.19
    Negative Logits
    ornia
    -0.70
    hap
    -0.67
    laws
    -0.65
     Mens
    -0.63
    ignt
    -0.63
     artificial
    -0.62
    leaning
    -0.62
    agles
    -0.62
    inois
    -0.62
    elsius
    -0.61
    POSITIVE LOGITS
    pad
    0.95
    wright
    0.92
    book
    0.91
    makers
    0.90
    stores
    0.89
    store
    0.89
    plan
    0.89
    maker
    0.89
    books
    0.88
     creator
    0.88
    Activations Density 4.609%

    No Known Activations