© 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. 3172
    Prev
    Next
    INDEX
    Explanations

    ingredients and instructions in a recipe

    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
    680
    +0.12
    0.5%
    628
    +0.12
    0.5%
    259
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.12
    0.02
    238
    +0.12
    0.02
    81
    +0.11
    0.02
    Negative Logits
    hement
    -0.77
    \<
    -0.63
    emis
    -0.61
    Gene
    -0.61
     Leilan
    -0.60
     fort
    -0.59
    Feed
    -0.59
    maxwell
    -0.58
    FY
    -0.56
    oslav
    -0.56
    POSITIVE LOGITS
    etimes
    0.78
    Ħ¢
    0.74
     )]
    0.72
    \\\\\\\\
    0.71
    pires
    0.68
    ities
    0.67
    ths
    0.66
     inches
    0.65
    rencies
    0.64
     requests
    0.64
    Activations Density 0.077%

    No Known Activations