© 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. 3098
    Prev
    Next
    INDEX
    Explanations

    verbs related to successful actions or achievements

    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
    151
    +0.14
    0.6%
    551
    +0.12
    0.5%
    225
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.14
    0.07
    551
    +0.12
    0.05
    225
    +0.10
    0.04
    Negative Logits
    soc
    -0.79
     favourites
    -0.75
     enthus
    -0.67
    Liter
    -0.67
    icip
    -0.67
    amy
    -0.66
     favorites
    -0.65
     Sight
    -0.65
     tendency
    -0.64
     pecul
    -0.62
    POSITIVE LOGITS
     transitioned
    0.99
     reproduce
    0.99
     lobbied
    0.94
     communicated
    0.93
     reinvent
    0.92
    ãĤ©
    0.88
     awoken
    0.88
     transported
    0.87
     overcame
    0.87
     integrate
    0.87
    Activations Density 0.134%

    No Known Activations