© 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. 14829
    Prev
    Next
    INDEX
    Explanations

    references to family relationships

    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
    87
    +0.49
    4.0%
    464
    +0.13
    1.0%
    459
    +0.10
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.49
    -0.03
    87
    +0.13
    -0.01
    208
    +0.10
    0.06
    Negative Logits
     Classification
    -0.35
    RESULTS
    -0.34
     dracon
    -0.34
    abase
    -0.34
     unaccount
    -0.34
    alties
    -0.31
    rats
    -0.31
    terness
    -0.30
     Spiel
    -0.30
    catentry
    -0.30
    POSITIVE LOGITS
    iframe
    0.40
     embed
    0.36
    Subscribe
    0.36
    Pinterest
    0.34
     Ø
    0.33
    LinkedIn
    0.33
    Month
    0.33
    push
    0.32
    Mu
    0.32
    Inf
    0.32
    Activations Density 0.550%

    No Known Activations