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

    Neuronpedia

    APICircuit 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. 21682
    Prev
    Next
    INDEX
    Explanations

    information related to sports teams, alliances, and partnerships

    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
    373
    +0.14
    0.6%
    334
    +0.12
    0.5%
    100
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.14
    0.03
    43
    +0.12
    0.02
    530
    +0.11
    0.02
    Negative Logits
    zers
    -0.77
    worldly
    -0.75
    cards
    -0.73
     informants
    -0.69
    sth
    -0.67
    cript
    -0.67
    ources
    -0.66
    uders
    -0.65
    oner
    -0.65
    heim
    -0.64
    POSITIVE LOGITS
     Sierra
    0.87
     MPH
    0.81
     Kinnikuman
    0.77
     Ministry
    0.77
     Programming
    0.76
     NEC
    0.73
     Communication
    0.72
     Durham
    0.71
     Carnegie
    0.71
     USAF
    0.71
    Activations Density 0.120%

    No Known Activations