© 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. 15034
    Prev
    Next
    INDEX
    Explanations

    information related to news articles and current 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
    606
    +0.13
    0.6%
    181
    +0.10
    0.4%
    482
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.13
    0.04
    181
    +0.10
    0.04
    482
    +0.10
    0.04
    Negative Logits
     ().
    -0.72
    $.
    -0.72
    Contents
    -0.71
    Ire
    -0.68
    common
    -0.68
    ÙĴ
    -0.68
     Morty
    -0.65
    material
    -0.65
    ãĢĤ
    -0.64
    âĹ¼
    -0.63
    POSITIVE LOGITS
     Says
    1.09
     slams
    1.06
     reacts
    1.02
     Gets
    0.95
     shuts
    0.95
     approves
    0.95
     defends
    0.94
     Reported
    0.90
     Goes
    0.89
     warns
    0.88
    Activations Density 0.372%

    No Known Activations