© 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. 14932
    Prev
    Next
    INDEX
    Explanations

    I'm unable to provide a summary as there are multiple different activations present across this neuron's activations

    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
    480
    +0.27
    1.3%
    447
    +0.26
    1.3%
    481
    +0.19
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.27
    0.05
    480
    +0.26
    0.02
    464
    +0.19
    0.05
    Negative Logits
     Instr
    -0.91
     Ninth
    -0.76
     Seym
    -0.71
     Borders
    -0.71
     Fundamental
    -0.70
     Canary
    -0.66
     undermin
    -0.66
     predec
    -0.65
     Mayo
    -0.65
     Chatt
    -0.65
    POSITIVE LOGITS
    @
    1.10
    _
    1.06
    ":{"
    0.89
    podcast
    0.84
    info
    0.84
    oft
    0.80
    ql
    0.78
    _-_
    0.78
    __
    0.78
    reports
    0.77
    Activations Density 0.279%

    No Known Activations