© 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. 3845
    Prev
    Next
    INDEX
    Explanations

    instances of the word "even" when used emphatically or as a point of comparison

    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
    277
    +0.09
    0.4%
    133
    +0.09
    0.4%
    99
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    133
    +0.09
    0.03
    277
    +0.09
    0.03
    108
    +0.09
    0.03
    Negative Logits
    aim
    -0.91
    Ĥİ
    -0.85
    idelines
    -0.82
    cent
    -0.80
    ffen
    -0.79
    rend
    -0.77
    ayers
    -0.77
    isen
    -0.75
    unity
    -0.74
    acker
    -0.73
    POSITIVE LOGITS
     remotely
    0.90
     outright
    0.82
     stranger
    0.77
     though
    0.76
    handedly
    0.75
     tho
    0.73
    monary
    0.70
     worse
    0.69
     strangers
    0.66
     downright
    0.65
    Activations Density 0.041%

    No Known Activations