© 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. 15316
    Prev
    Next
    INDEX
    Explanations

    words related to physical impact or collision

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    187
    +0.13
    0.6%
    526
    +0.11
    0.5%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.13
    0.01
    526
    +0.11
    0.01
    187
    +0.11
    0.01
    Negative Logits
     ministry
    -0.71
    eval
    -0.70
    encia
    -0.70
    ANCE
    -0.69
    ufact
    -0.68
    RIP
    -0.65
    ILLE
    -0.64
     Ecology
    -0.63
    vation
    -0.62
    éĸ
    -0.61
    POSITIVE LOGITS
     bump
    0.92
     bumps
    0.87
    olean
    0.85
    saw
    0.83
    balls
    0.83
    wagon
    0.82
    kins
    0.82
    stairs
    0.81
    eting
    0.81
    sticks
    0.80
    Activations Density 0.036%

    No Known Activations