© 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. 15466
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations, such as cities, departments, and school districts

    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
    251
    +0.12
    0.5%
    331
    +0.11
    0.5%
    602
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.12
    0.06
    288
    +0.11
    0.06
    488
    +0.10
    0.05
    Negative Logits
    linger
    -0.86
    iphate
    -0.82
    issan
    -0.82
    thora
    -0.79
    ription
    -0.77
    undrum
    -0.77
    jen
    -0.76
    agonist
    -0.76
    vironment
    -0.73
    enza
    -0.73
    POSITIVE LOGITS
     officials
    1.21
     insiders
    1.14
     employees
    1.13
     staffers
    1.13
    wide
    1.08
     personnel
    1.04
     regulars
    1.01
     offices
    1.00
     administrators
    1.00
     coffers
    0.98
    Activations Density 0.257%

    No Known Activations