© 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. 3882
    Prev
    Next
    INDEX
    Explanations

    details and descriptions of events, particularly related to security measures and literary works

    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
    87
    +0.27
    1.3%
    544
    +0.08
    0.4%
    264
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.27
    -0.04
    575
    +0.08
    0.08
    225
    +0.08
    0.07
    Negative Logits
    "!
    -0.60
    Rated
    -0.56
    `.
    -0.53
    anwhile
    -0.53
    oya
    -0.53
    .''.
    -0.51
    .�
    -0.51
     Advertisement
    -0.51
    .''
    -0.50
    .}
    -0.49
    POSITIVE LOGITS
     (),
    0.88
    ?,
    0.88
    ,[
    0.79
    *,
    0.73
    +,
    0.67
    %,
    0.65
     ,
    0.63
    ®,
    0.61
    !,
    0.59
    (),
    0.59
    Activations Density 1.442%

    No Known Activations