© 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. 15317
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation or gratitude

    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
    715
    +0.10
    0.4%
    521
    +0.09
    0.4%
    284
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    521
    +0.10
    0.01
    285
    +0.09
    0.01
    317
    +0.09
    0.01
    Negative Logits
    infect
    -0.92
    buster
    -0.81
    prep
    -0.78
    rooms
    -0.74
    ridden
    -0.73
    metal
    -0.73
    shr
    -0.71
    mares
    -0.70
    Ult
    -0.70
    sol
    -0.69
    POSITIVE LOGITS
     appreciation
    0.94
    ĸļ
    0.92
     contributions
    0.80
     compliments
    0.77
    ably
    0.74
    ¿½
    0.73
     appreciate
    0.73
     gifts
    0.72
     advances
    0.72
    reciation
    0.71
    Activations Density 0.028%

    No Known Activations