© 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. 3714
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to regulations and proposals in a formal context

    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
    94
    +0.12
    0.5%
    341
    +0.12
    0.5%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    644
    +0.12
    0.04
    94
    +0.12
    0.04
    267
    +0.11
    0.04
    Negative Logits
    20439
    -0.91
    grave
    -0.83
    cest
    -0.76
    miss
    -0.75
     regrets
    -0.73
     renewed
    -0.72
    ashington
    -0.71
     tears
    -0.70
    arranted
    -0.70
    akening
    -0.68
    POSITIVE LOGITS
     nutshell
    1.07
     gist
    1.04
    Basically
    0.98
    Setup
    0.96
     Basically
    0.95
     premise
    0.94
     Essentially
    0.92
     revolves
    0.88
     simple
    0.88
     Setup
    0.88
    Activations Density 0.373%

    No Known Activations