© 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. 14830
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to famous 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
    481
    +0.29
    1.4%
    430
    +0.14
    0.6%
    762
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.29
    0.07
    700
    +0.14
    0.07
    659
    +0.09
    0.07
    Negative Logits
    /-
    -0.69
    ãĥ´ãĤ¡
    -0.68
    Load
    -0.63
     Palest
    -0.61
    ãĥ¼ãĥĨ
    -0.61
    Els
    -0.59
    ãĥ¼ãĥĨãĤ£
    -0.58
    ãĤ¹
    -0.57
    ipl
    -0.56
    duction
    -0.56
    POSITIVE LOGITS
     joins
    1.02
     welcomed
    1.01
     attends
    0.99
     agrees
    0.96
     urged
    0.96
     reacted
    0.95
     warned
    0.95
     teamed
    0.93
     believes
    0.91
     condemned
    0.90
    Activations Density 0.294%

    No Known Activations