© 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. 15529
    Prev
    Next
    INDEX
    Explanations

    action verbs related to technological innovations and capabilities

    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
    551
    +0.14
    0.7%
    718
    +0.09
    0.4%
    139
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.14
    0.08
    139
    +0.09
    0.05
    718
    +0.09
    0.05
    Negative Logits
     Lauder
    -0.80
     Irving
    -0.69
    rant
    -0.69
     hating
    -0.66
     Tradition
    -0.65
     Reasons
    -0.62
     Brent
    -0.61
     Sunset
    -0.61
     Darling
    -0.61
     Gus
    -0.61
    POSITIVE LOGITS
    't
    1.33
     withstand
    1.26
    adian
    1.21
    berra
    1.15
     penetrate
    1.10
     handle
    1.08
     afford
    1.07
    NOT
    1.01
     easily
    1.00
     operate
    0.99
    Activations Density 0.135%

    No Known Activations