© 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. 15433
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames preceded by '@'

    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
    314
    +0.15
    0.7%
    373
    +0.14
    0.6%
    640
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    434
    +0.15
    0.03
    107
    +0.14
    0.03
    518
    +0.11
    0.03
    Negative Logits
     Takeru
    -0.73
     Norwich
    -0.72
     specificity
    -0.72
     nasal
    -0.70
     slips
    -0.67
     malaria
    -0.66
     Lyme
    -0.65
     artic
    -0.64
     orche
    -0.64
     displacement
    -0.64
    POSITIVE LOGITS
    realDonaldTrump
    1.15
    Real
    1.05
    username
    1.03
    Official
    1.02
    ANI
    0.99
    thereal
    0.94
    Coach
    0.93
    stats
    0.90
    Truth
    0.90
    #$
    0.88
    Activations Density 0.016%

    No Known Activations