© 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 49152
    9. 8-RES_FS49152-JB
    11. 25990
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    447
    +0.11
    0.5%
    464
    +0.11
    0.5%
    124
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.11
    0.03
    120
    +0.11
    0.03
    530
    +0.11
    0.02
    Negative Logits
    conn
    -0.78
    weet
    -0.74
    nels
    -0.73
    wu
    -0.72
    lis
    -0.71
     toget
    -0.70
    Cola
    -0.70
    wreck
    -0.69
    kel
    -0.69
    hov
    -0.68
    POSITIVE LOGITS
     Definitions
    1.06
     Specifications
    1.02
     Description
    1.02
     Directions
    0.98
     Abilities
    0.98
     Evaluation
    0.98
     characteristics
    0.96
     Distribution
    0.96
     Usage
    0.95
     Features
    0.94
    Activations Density 0.071%

    No Known Activations