© 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. 3647
    Prev
    Next
    INDEX
    Explanations

    words related to recovery and return to work or activity after a physical setback

    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
    271
    +0.14
    0.6%
    469
    +0.11
    0.5%
    202
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.14
    0.05
    416
    +0.11
    0.03
    74
    +0.10
    0.04
    Negative Logits
     empires
    -0.94
     Capitalism
    -0.89
     Nobel
    -0.85
     monopoly
    -0.84
     Governments
    -0.82
     monopol
    -0.82
     Rothschild
    -0.81
     imperialist
    -0.80
     Genocide
    -0.78
     Prohibition
    -0.78
    POSITIVE LOGITS
     workouts
    1.38
     preseason
    1.34
     offseason
    1.29
     rehab
    1.26
     scrimmage
    1.23
     workout
    1.21
    Coach
    1.20
     rookies
    1.17
     teammates
    1.14
    juries
    1.11
    Activations Density 0.683%

    No Known Activations