© 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. 3711
    Prev
    Next
    INDEX
    Explanations

    information related to locations and events

    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
    378
    +0.11
    0.5%
    109
    +0.10
    0.4%
    728
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.11
    0.04
    482
    +0.10
    0.04
    232
    +0.10
    0.04
    Negative Logits
     Garry
    -0.86
    ANN
    -0.77
    ann
    -0.77
     Ame
    -0.76
     Aval
    -0.75
     acknow
    -0.74
     Ao
    -0.70
     Banana
    -0.68
     Dota
    -0.68
    gie
    -0.67
    POSITIVE LOGITS
    EStreamFrame
    0.86
    STEM
    0.85
    tnc
    0.77
    erm
    0.77
    º
    0.76
    eros
    0.74
    zed
    0.73
    ument
    0.72
    Jer
    0.72
    ³³³³³³³³
    0.71
    Activations Density 0.215%

    No Known Activations