© 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. 15444
    Prev
    Next
    INDEX
    Explanations

    negative events or issues causing disturbances, such as accidents, casualties, outages, and problems

    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
    23
    +0.09
    0.4%
    172
    +0.09
    0.4%
    675
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.09
    0.03
    260
    +0.09
    0.03
    252
    +0.09
    0.02
    Negative Logits
    essor
    -0.72
    alan
    -0.70
    uthor
    -0.69
    adobe
    -0.68
    enhagen
    -0.67
     wisely
    -0.66
    ablish
    -0.66
    orest
    -0.66
    bold
    -0.65
    nesday
    -0.64
    POSITIVE LOGITS
     havoc
    1.45
     headaches
    1.13
     disturbance
    1.08
     uproar
    1.07
     damage
    1.04
     mayhem
    1.00
     unnecessary
    0.97
     stir
    0.96
     harm
    0.96
     disruption
    0.95
    Activations Density 0.156%

    No Known Activations