© 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. 3950
    Prev
    Next
    INDEX
    Explanations

    technical instructions related to software installation

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.26
    1.3%
    481
    +0.18
    0.9%
    587
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.26
    -0.01
    308
    +0.18
    0.03
    368
    +0.09
    0.04
    Negative Logits
     overload
    -0.68
     trap
    -0.66
     traps
    -0.65
     applic
    -0.64
     elim
    -0.60
     glac
    -0.58
     probe
    -0.58
     urgency
    -0.57
     sparse
    -0.56
     contag
    -0.56
    POSITIVE LOGITS
    Jr
    0.89
    reciation
    0.84
    aeper
    0.84
    ÃĥÃĤ
    0.83
    ÃĥÃĤÃĥÃĤ
    0.78
    History
    0.75
     pione
    0.70
    psons
    0.70
    ¯
    0.69
    æĸ¹
    0.69
    Activations Density 0.795%

    No Known Activations