© 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. 3156
    Prev
    Next
    INDEX
    Explanations

    terms related to dietary and health advice, medical conditions, legal actions, and technology requirements

    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
    87
    +0.37
    2.0%
    711
    +0.09
    0.5%
    314
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    711
    +0.37
    0.06
    87
    +0.09
    -0.02
    288
    +0.08
    0.10
    Negative Logits
    lees
    -0.79
    ernels
    -0.79
    rencies
    -0.77
     Machines
    -0.76
    hops
    -0.75
    casts
    -0.72
    urches
    -0.72
    units
    -0.72
     Rooms
    -0.71
    rooms
    -0.71
    POSITIVE LOGITS
     standpoint
    0.90
     version
    0.72
     perspective
    0.72
     dose
    0.70
     regimen
    0.70
     foothold
    0.70
     statement
    0.68
     degree
    0.67
     approximation
    0.66
     arrangement
    0.66
    Activations Density 0.952%

    No Known Activations