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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19583
    Prev
    Next
    INDEX
    Explanations

    prepositions 'of' and 'in' followed by numbers indicating amounts or quantities

    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
    625
    +0.10
    0.4%
    481
    +0.10
    0.4%
    323
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.10
    0.03
    557
    +0.10
    0.03
    587
    +0.09
    0.03
    Negative Logits
    ONSORED
    -0.84
    utherland
    -0.71
    lege
    -0.69
    wake
    -0.69
    ESA
    -0.68
    Allah
    -0.68
    UTC
    -0.68
    utenberg
    -0.67
    SCP
    -0.67
    ACT
    -0.66
    POSITIVE LOGITS
    erous
    1.29
     behalf
    1.12
     anything
    0.73
     arrival
    0.71
     Saturdays
    0.70
     individuality
    0.69
    shore
    0.69
     completing
    0.68
     impulse
    0.68
     eBay
    0.67
    Activations Density 0.139%

    No Known Activations