© 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. 15321
    Prev
    Next
    INDEX
    Explanations

    medical terms related to various health conditions and treatments

    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
    208
    +0.13
    0.6%
    516
    +0.09
    0.4%
    363
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.13
    0.03
    208
    +0.09
    0.03
    738
    +0.09
    0.03
    Negative Logits
     Mahjong
    -0.74
    Money
    -0.74
     Rules
    -0.71
     Grounds
    -0.70
    ãĤ±
    -0.70
     Shades
    -0.70
     Money
    -0.69
     Wonders
    -0.67
     Powers
    -0.66
    Dash
    -0.66
    POSITIVE LOGITS
    emia
    1.23
    rosis
    1.15
    ectomy
    1.13
    iasis
    1.10
    itis
    1.08
    opathy
    1.06
     vascular
    1.06
    osis
    1.05
    ascular
    1.04
    clerosis
    1.03
    Activations Density 0.103%

    No Known Activations