© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 3944
    Prev
    Next
    INDEX
    Explanations

    examples of financial transactions and arrangements, such as expenditure, writing letters related to purchases, translation services, and financial rules

    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
    87
    +0.44
    2.5%
    447
    +0.34
    1.9%
    64
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.44
    -0.02
    407
    +0.34
    0.05
    317
    +0.14
    0.06
    Negative Logits
    ranch
    -0.46
    SAN
    -0.46
    Born
    -0.45
    erenn
    -0.45
    iership
    -0.44
     sprawling
    -0.42
     Cups
    -0.42
    ylum
    -0.41
    pmwiki
    -0.39
    ahime
    -0.39
    POSITIVE LOGITS
     therefore
    0.79
     moreover
    0.71
     furthermore
    0.69
    anwhile
    0.65
     however
    0.63
     Lastly
    0.62
    CONCLUS
    0.57
    sequently
    0.56
     thus
    0.55
    ogether
    0.54
    Activations Density 2.102%

    No Known Activations