© 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 49152
    9. 8-RES_FS49152-JB
    11. 25979
    Prev
    Next
    INDEX
    Explanations

    references to ethnic conflict and violence

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    154
    +0.14
    0.7%
    711
    +0.11
    0.5%
    1
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.14
    0.06
    711
    +0.11
    0.03
    109
    +0.09
    0.04
    Negative Logits
     Cosponsors
    -0.81
     Folder
    -0.78
    Cert
    -0.75
    Premium
    -0.74
     Collider
    -0.74
    TABLE
    -0.73
    rawdownloadcloneembedreportprint
    -0.73
    mith
    -0.71
    PLIC
    -0.71
    Lear
    -0.71
    POSITIVE LOGITS
     insurgency
    1.21
     separatists
    1.15
     rebels
    1.15
     insurgents
    1.15
     insurgent
    1.13
     militants
    1.10
     uprising
    1.09
     separatist
    1.08
     siege
    1.08
     Islamist
    1.08
    Activations Density 0.373%

    No Known Activations