© 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. 15338
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in specific situations or dialogues

    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%
    78
    +0.10
    0.4%
    502
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.13
    0.01
    200
    +0.10
    0.01
    224
    +0.09
    0.01
    Negative Logits
    enance
    -0.80
    ged
    -0.76
    gement
    -0.76
    ortmund
    -0.71
    inals
    -0.71
    atical
    -0.68
    ocard
    -0.66
    ging
    -0.66
    udeb
    -0.65
    ItemTracker
    -0.63
    POSITIVE LOGITS
     Carter
    0.86
    bilt
    0.83
    isle
    0.74
    hawks
    0.73
     Solo
    0.72
    lee
    0.72
    Carter
    0.72
    wick
    0.72
    pan
    0.71
     III
    0.71
    Activations Density 0.016%

    No Known Activations