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 49152
    5. 8-RES_FS49152-JB
    6. 26435
    Prev
    Next
    INDEX
    Explanations

    mentions of automotive brands and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    481
    +0.14
    0.6%
    447
    +0.12
    0.6%
    343
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.14
    0.01
    500
    +0.12
    0.01
    513
    +0.12
    0.01
    Negative Logits
    omaly
    -0.77
    chin
    -0.69
    tale
    -0.69
    geoning
    -0.67
    abilities
    -0.67
    xual
    -0.67
    κ
    -0.66
    ablishment
    -0.66
    redd
    -0.65
    oldemort
    -0.65
    POSITIVE LOGITS
    sburg
    0.95
    shire
    0.86
     Lumpur
    0.78
     Technologies
    0.73
     Motor
    0.69
     Benz
    0.68
    sburgh
    0.66
    SEA
    0.66
     Racing
    0.66
    intosh
    0.65
    Activations Density 0.005%

    No Known Activations