© 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. 15368
    Prev
    Next
    INDEX
    Explanations

    economic terms and scenarios such as income inequality and financial regulations

    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
    288
    +0.13
    0.6%
    116
    +0.12
    0.6%
    642
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.02
    326
    +0.12
    0.02
    614
    +0.12
    0.01
    Negative Logits
    çīĪ
    -0.92
    acho
    -0.82
    ãĥ¼ãĥ³
    -0.79
    女
    -0.66
    gments
    -0.66
    ahu
    -0.66
    ãĤ·ãĥ£
    -0.65
     è£ıç
    -0.63
    atana
    -0.63
     literal
    -0.62
    POSITIVE LOGITS
     awhile
    0.76
    tenance
    0.76
     indefinitely
    0.71
     stall
    0.70
    luster
    0.70
     simmer
    0.69
    emate
    0.67
     motion
    0.66
    manship
    0.64
    rift
    0.63
    Activations Density 0.042%

    No Known Activations