© 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. 3336
    Prev
    Next
    INDEX
    Explanations

    information related to data and statistics

    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
    480
    +0.52
    2.7%
    266
    +0.11
    0.6%
    314
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.52
    0.00
    266
    +0.11
    0.08
    655
    +0.09
    0.04
    Negative Logits
     authent
    -0.59
     voic
    -0.58
     Mous
    -0.57
     blasp
    -0.56
     oath
    -0.55
     spies
    -0.55
     grate
    -0.54
     vend
    -0.53
     discreet
    -0.53
     Garage
    -0.53
    POSITIVE LOGITS
    verages
    0.84
    Chart
    0.83
     Adjusted
    0.78
    Ranked
    0.77
     adjusted
    0.77
    adjusted
    0.76
    flation
    0.76
    ulia
    0.76
     averages
    0.76
     Gallup
    0.74
    Activations Density 0.945%

    No Known Activations