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. 11451
    Prev
    Next
    INDEX
    Explanations

    terms related to economic growth

    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
    216
    +0.14
    0.7%
    459
    +0.13
    0.6%
    670
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    670
    +0.14
    0.03
    216
    +0.13
    0.03
    439
    +0.13
    0.02
    Negative Logits
    nee
    -0.92
    CLA
    -0.76
    netflix
    -0.76
    ãĥīãĥ©
    -0.71
    ridge
    -0.69
    nery
    -0.69
    POS
    -0.68
    pper
    -0.67
    opol
    -0.67
    Ò
    -0.65
    POSITIVE LOGITS
    rates
    1.05
     prospects
    0.95
     rates
    0.94
     Rates
    0.94
     promot
    0.90
     rate
    0.85
     slowdown
    0.79
    atform
    0.78
    rate
    0.78
     growth
    0.76
    Activations Density 0.032%

    No Known Activations