© 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. 2994
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluation and ranking based on assigned values

    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
    332
    +0.10
    0.5%
    235
    +0.10
    0.4%
    526
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.10
    0.07
    362
    +0.10
    0.06
    526
    +0.09
    -0.00
    Negative Logits
     departments
    -0.77
    iencies
    -0.71
     channels
    -0.70
     strains
    -0.70
    ities
    -0.67
    paces
    -0.66
    riages
    -0.66
     establishments
    -0.64
     piles
    -0.64
    nces
    -0.63
    POSITIVE LOGITS
     theirs
    0.74
     oneself
    0.69
    lier
    0.67
     Scarlet
    0.63
     Wonderland
    0.62
    EStreamFrame
    0.62
     Perspective
    0.61
    hillary
    0.60
    rontal
    0.60
    ãĤĭ
    0.60
    Activations Density 0.451%

    No Known Activations