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. 23674
    Prev
    Next
    INDEX
    Explanations

    monetary values and quantities

    oai_token-act-pair · gpt-4o-miniTriggered 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
    447
    +0.30
    1.5%
    480
    +0.25
    1.2%
    481
    +0.21
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.30
    0.05
    464
    +0.25
    0.04
    266
    +0.21
    0.04
    Negative Logits
     Vaugh
    -0.65
    nesday
    -0.63
     advoc
    -0.62
    jri
    -0.61
     princ
    -0.61
     withd
    -0.60
    akespe
    -0.59
     disadvant
    -0.59
    ãĤ´ãĥ³
    -0.58
    bye
    -0.58
    POSITIVE LOGITS
     Amount
    0.71
     Estimated
    0.68
     Donation
    0.68
    Percent
    0.67
     SHARES
    0.67
     Cosponsors
    0.65
     Coup
    0.64
     Increase
    0.61
     Discount
    0.61
     Increases
    0.61
    Activations Density 0.169%

    No Known Activations