© 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. 3912
    Prev
    Next
    INDEX
    Explanations

    words related to historical events and disputes related to payments or obligations

    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
    756
    +0.10
    0.5%
    35
    +0.10
    0.4%
    360
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.10
    -0.01
    718
    +0.10
    0.04
    268
    +0.10
    0.02
    Negative Logits
    Package
    -0.75
    OUP
    -0.75
    Products
    -0.73
    Stats
    -0.71
    VIDEO
    -0.71
    package
    -0.70
    PDATE
    -0.69
    oaded
    -0.69
    Delivery
    -0.68
    Edited
    -0.67
    POSITIVE LOGITS
     widened
    1.01
     widening
    0.99
     wid
    0.98
     deline
    0.97
     bounds
    0.94
     separating
    0.94
     cracks
    0.93
     narrowing
    0.93
     wedge
    0.90
     brid
    0.89
    Activations Density 0.390%

    No Known Activations