© 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. 14979
    Prev
    Next
    INDEX
    Explanations

    unusual situations or events

    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
    271
    +0.15
    0.7%
    284
    +0.10
    0.5%
    724
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.15
    0.03
    151
    +0.10
    0.03
    284
    +0.10
    0.03
    Negative Logits
    elsen
    -0.81
    claimer
    -0.77
    ushima
    -0.77
    burgh
    -0.72
    sheets
    -0.70
    inders
    -0.66
    uel
    -0.66
    ruction
    -0.65
    adr
    -0.63
    onest
    -0.63
    POSITIVE LOGITS
    ities
    1.09
    worldly
    0.99
    ties
    0.98
     circumstances
    0.96
     occurrences
    0.95
    ity
    0.90
    ITIES
    0.87
    ITY
    0.79
     circumstance
    0.78
     occurrence
    0.77
    Activations Density 0.061%

    No Known Activations