© 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. 3239
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific entities or proper nouns, especially those with proper names like "The Apothe"car"ium"

    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
    343
    +0.13
    0.6%
    377
    +0.12
    0.6%
    82
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.13
    0.02
    705
    +0.12
    0.02
    597
    +0.10
    0.02
    Negative Logits
    enegger
    -0.75
     Hurricanes
    -0.70
    fast
    -0.67
    neck
    -0.66
     Sands
    -0.65
     Lauder
    -0.65
    WHERE
    -0.64
     Instruments
    -0.62
     fluids
    -0.61
     Sins
    -0.61
    POSITIVE LOGITS
    artment
    1.49
    athetic
    1.39
    ocaly
    1.33
    ollo
    1.32
    ocalyptic
    1.31
    athy
    1.27
    ocry
    1.26
    ocalypse
    1.21
    olitical
    1.19
    otrop
    1.15
    Activations Density 0.023%

    No Known Activations