© 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. 14888
    Prev
    Next
    INDEX
    Explanations

    information related to controversial social or political issues and responses to those issues

    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
    102
    +0.17
    0.8%
    55
    +0.12
    0.6%
    718
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.17
    0.10
    55
    +0.12
    0.08
    718
    +0.10
    0.07
    Negative Logits
     Flavoring
    -1.08
    ngth
    -0.98
    essor
    -0.81
     Awakens
    -0.79
     openings
    -0.73
    rosis
    -0.69
    ividual
    -0.67
     Releases
    -0.67
     throats
    -0.65
    plings
    -0.65
    POSITIVE LOGITS
     evident
    1.03
     prevalent
    0.94
     irrelevant
    0.93
     dependent
    0.93
     commonplace
    0.92
     predictable
    0.92
     feasible
    0.91
     understandable
    0.90
     applicable
    0.90
     fraught
    0.90
    Activations Density 0.295%

    No Known Activations