© 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. 3291
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various individuals

    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
    447
    +0.14
    0.7%
    314
    +0.13
    0.6%
    744
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.06
    317
    +0.13
    0.04
    346
    +0.10
    0.04
    Negative Logits
    LEASE
    -0.64
     CFL
    -0.63
     toler
    -0.61
     lockout
    -0.60
     Celest
    -0.56
     pesky
    -0.56
     attachments
    -0.55
    geries
    -0.55
     occasional
    -0.55
    iencies
    -0.55
    POSITIVE LOGITS
     replied
    0.92
    ONSORED
    0.86
     (@
    0.86
     exclaimed
    0.86
     remarked
    0.85
     joked
    0.84
     said
    0.82
    said
    0.80
     proverb
    0.79
    Said
    0.76
    Activations Density 0.217%

    No Known Activations