© 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. 15086
    Prev
    Next
    INDEX
    Explanations

    information related to relationships and diplomatic ties between countries

    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
    340
    +0.11
    0.5%
    493
    +0.10
    0.5%
    673
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.11
    0.04
    170
    +0.10
    0.03
    528
    +0.10
    0.03
    Negative Logits
    odder
    -0.68
     mills
    -0.65
     peanuts
    -0.65
    rpm
    -0.65
     launchers
    -0.65
     nails
    -0.64
     racks
    -0.63
    ãĤº
    -0.63
     Shelter
    -0.63
     ineligible
    -0.63
    POSITIVE LOGITS
     mutual
    1.35
     mutually
    1.28
    between
    1.23
     between
    1.19
     friendship
    1.16
    ilateral
    1.10
     friendships
    1.08
    relations
    1.06
    Relations
    1.06
     relationship
    1.05
    Activations Density 0.355%

    No Known Activations