© 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. 15528
    Prev
    Next
    INDEX
    Explanations

    terms related to technological advancements and their impacts on various industries

    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
    288
    +0.14
    0.7%
    642
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.14
    0.03
    288
    +0.11
    0.03
    472
    +0.10
    0.02
    Negative Logits
    ãĥ£
    -0.72
    bia
    -0.70
    respective
    -0.68
    ramid
    -0.65
    lua
    -0.64
    ric
    -0.63
    cemic
    -0.62
    gur
    -0.61
    mop
    -0.61
     Upton
    -0.60
    POSITIVE LOGITS
    hower
    0.92
     technologies
    0.84
     advancements
    0.84
     breakthrough
    0.82
     advances
    0.81
     discoveries
    0.79
     leaps
    0.78
     Invention
    0.77
     innovations
    0.75
    ments
    0.75
    Activations Density 0.068%

    No Known Activations