Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11364
    Prev
    Next
    INDEX
    Explanations

    technology-related terms and software names

    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
    288
    +0.15
    0.7%
    496
    +0.14
    0.7%
    603
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.01
    288
    +0.14
    0.01
    294
    +0.09
    0.01
    Negative Logits
    erest
    -0.70
    enza
    -0.69
    sie
    -0.69
    erent
    -0.68
    ioxide
    -0.68
    女
    -0.67
    iologist
    -0.67
     Lama
    -0.66
     Vaugh
    -0.64
    eren
    -0.64
    POSITIVE LOGITS
     browsers
    0.93
     Firefox
    0.88
     browser
    0.86
     OS
    0.83
     Browser
    0.77
    browser
    0.76
    ĺħ
    0.76
     addon
    0.75
     Extensions
    0.74
    BSD
    0.73
    Activations Density 0.014%

    No Known Activations