© 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. 3342
    Prev
    Next
    INDEX
    Explanations

    technical language related to software development and engineering

    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
    134
    +0.12
    0.6%
    580
    +0.12
    0.5%
    108
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.12
    0.07
    566
    +0.12
    0.06
    49
    +0.11
    0.06
    Negative Logits
    erence
    -0.64
     Seah
    -0.63
     Revival
    -0.61
     Ake
    -0.61
     Saunders
    -0.60
     Showdown
    -0.60
     submissions
    -0.60
     Convention
    -0.59
     Silent
    -0.59
    soType
    -0.58
    POSITIVE LOGITS
     effectively
    1.04
     efficiently
    1.02
     able
    0.93
     effortlessly
    0.91
     achieve
    0.90
     confidently
    0.89
     successfully
    0.89
     propel
    0.88
     safely
    0.87
     streng
    0.85
    Activations Density 0.420%

    No Known Activations