© 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. 3717
    Prev
    Next
    INDEX
    Explanations

    locations or actions related to criminal activities

    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
    309
    +0.13
    0.6%
    224
    +0.12
    0.6%
    587
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.13
    0.05
    70
    +0.12
    0.05
    424
    +0.12
    0.03
    Negative Logits
     penchant
    -0.68
    catentry
    -0.67
     Simply
    -0.65
     Definitely
    -0.64
     Subtle
    -0.64
     Thumbnails
    -0.63
    quickShipAvailable
    -0.62
    etheless
    -0.62
    £ı
    -0.59
     ISBN
    -0.59
    POSITIVE LOGITS
    achu
    0.71
    oti
    0.71
    BIL
    0.70
     belongings
    0.68
    orate
    0.67
    ezvous
    0.67
    igate
    0.66
    abil
    0.65
    fix
    0.64
    eline
    0.64
    Activations Density 0.237%

    No Known Activations