© 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. 15005
    Prev
    Next
    INDEX
    Explanations

    phrases related to cognitive performance and associated traits like mood, cognition, behavioral effects, and genetic variants

    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
    481
    +0.17
    0.8%
    575
    +0.12
    0.5%
    255
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.17
    0.06
    255
    +0.12
    0.05
    575
    +0.11
    0.06
    Negative Logits
    wered
    -0.73
     Franch
    -0.68
    ounty
    -0.68
    govtrack
    -0.64
     Bans
    -0.62
    osher
    -0.62
    ãĤ«
    -0.61
    bara
    -0.61
    annon
    -0.61
    said
    -0.60
    POSITIVE LOGITS
     impairment
    1.00
     traits
    0.94
     disorders
    0.94
     responsiveness
    0.93
    thood
    0.91
     behaviors
    0.91
     Disorders
    0.90
     enhancement
    0.88
     biomark
    0.88
     behaviours
    0.88
    Activations Density 0.168%

    No Known Activations