© 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. 14855
    Prev
    Next
    INDEX
    Explanations

    quotations and statements related to geopolitical tensions and international relations

    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
    454
    +0.10
    0.5%
    697
    +0.09
    0.4%
    132
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.10
    0.04
    397
    +0.09
    0.04
    492
    +0.09
    0.03
    Negative Logits
     Baron
    -0.68
     Fine
    -0.67
     mediation
    -0.63
     Shell
    -0.61
     Mund
    -0.60
     Uni
    -0.60
     Brig
    -0.59
     ARM
    -0.58
     arbitration
    -0.57
     Firm
    -0.57
    POSITIVE LOGITS
    enth
    0.79
    ":[
    0.76
    aped
    0.76
    ago
    0.75
     ought
    0.75
     did
    0.75
    self
    0.75
    've
    0.75
     normally
    0.74
    ever
    0.73
    Activations Density 0.126%

    No Known Activations