© 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. 15115
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making

    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
    480
    +0.48
    2.5%
    351
    +0.14
    0.7%
    393
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.48
    0.07
    0
    +0.14
    0.09
    484
    +0.10
    0.08
    Negative Logits
    abul
    -0.58
    actionDate
    -0.55
     Powered
    -0.55
    odcast
    -0.55
    owered
    -0.54
    ied
    -0.53
    zip
    -0.53
    agger
    -0.53
    EMS
    -0.53
    atan
    -0.52
    POSITIVE LOGITS
     secondly
    1.25
     hence
    1.20
     consequently
    1.20
     thus
    1.13
     therefore
    1.07
     thereby
    1.06
     furthermore
    0.92
     then
    0.87
     thence
    0.85
     THEN
    0.85
    Activations Density 0.449%

    No Known Activations