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. 1245
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to research and experiments

    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
    674
    +0.09
    0.4%
    678
    +0.09
    0.4%
    99
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.09
    0.04
    495
    +0.09
    0.04
    669
    +0.09
    0.04
    Negative Logits
    ulpt
    -0.79
    iquette
    -0.78
    undrum
    -0.72
    aws
    -0.70
    ä¸ī
    -0.70
     Murd
    -0.69
     Booker
    -0.68
    ón
    -0.67
     Struggle
    -0.67
     Filip
    -0.67
    POSITIVE LOGITS
     amounts
    1.33
     (>
    1.31
     quantities
    1.28
     doses
    1.21
     concentrations
    1.16
     (<
    1.13
     exposures
    1.08
     levels
    1.05
     distances
    1.03
     sized
    0.99
    Activations Density 0.185%

    No Known Activations