© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13826
    Prev
    Next
    INDEX
    Explanations

    phrases related to social gatherings or leisure activities involving drinks

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    685
    +0.11
    0.5%
    155
    +0.11
    0.5%
    337
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.11
    -0.00
    337
    +0.11
    0.03
    198
    +0.09
    0.03
    Negative Logits
    entity
    -0.71
     disproportion
    -0.69
     timelines
    -0.69
     governs
    -0.69
     valves
    -0.69
     membranes
    -0.68
     predictive
    -0.66
    ifer
    -0.66
     levers
    -0.65
     ammon
    -0.65
    POSITIVE LOGITS
     dinner
    1.35
     lunch
    1.17
     brunch
    1.16
     breakfast
    1.16
     supper
    1.14
     dinners
    1.13
     Dinner
    1.05
     spa
    1.04
     dessert
    1.03
     meal
    1.02
    Activations Density 0.458%

    No Known Activations