© 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. 15398
    Prev
    Next
    INDEX
    Explanations

    information related to music events, albums, and bands

    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
    427
    +0.12
    0.5%
    627
    +0.10
    0.4%
    346
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    427
    +0.12
    0.05
    627
    +0.10
    0.03
    749
    +0.09
    0.04
    Negative Logits
     taxpayers
    -0.85
     bureaucrats
    -0.80
     cler
    -0.77
     taxpayer
    -0.76
    Administ
    -0.75
    Study
    -0.75
     actu
    -0.74
     bureaucr
    -0.74
    Senator
    -0.74
     bribes
    -0.73
    POSITIVE LOGITS
     album
    1.47
     vocals
    1.43
     lyrics
    1.36
     albums
    1.35
     lyric
    1.29
     Songs
    1.29
     songs
    1.28
     bass
    1.27
     guitars
    1.26
     guitarist
    1.26
    Activations Density 0.765%

    No Known Activations