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. 610
    Prev
    Next
    INDEX
    Explanations

    JavaScript code related to mouse hover effects

    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
    83
    +0.10
    0.5%
    119
    +0.09
    0.4%
    617
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    345
    +0.10
    0.03
    326
    +0.09
    0.03
    83
    +0.09
    0.02
    Negative Logits
    terness
    -0.78
     Addiction
    -0.76
     Scotia
    -0.70
    Reloaded
    -0.69
     Chak
    -0.69
    gaard
    -0.69
     Nuclear
    -0.68
     MMR
    -0.67
     Dise
    -0.66
     Commodore
    -0.66
    POSITIVE LOGITS
    padding
    1.13
     caption
    1.06
     width
    1.05
    Content
    1.05
    "></
    1.04
    Style
    1.03
     padding
    1.01
    ></
    1.01
     styling
    0.98
     canvas
    0.97
    Activations Density 0.080%

    No Known Activations