© 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. 24160
    Prev
    Next
    INDEX
    Explanations

    prepositions, particularly "of" and "on"

    oai_token-act-pair · gpt-4o-miniTriggered 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
    608
    +0.12
    0.5%
    272
    +0.09
    0.4%
    587
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.12
    0.05
    272
    +0.09
    0.03
    298
    +0.09
    0.03
    Negative Logits
    iments
    -0.72
    isms
    -0.72
    agent
    -0.71
    iste
    -0.68
    Sport
    -0.67
    igent
    -0.64
    cht
    -0.64
    link
    -0.63
    wine
    -0.63
    heses
    -0.62
    POSITIVE LOGITS
     preserving
    1.26
     completing
    1.25
     keeping
    1.24
     releasing
    1.23
     getting
    1.22
     restoring
    1.20
     delivering
    1.20
     putting
    1.18
     contacting
    1.18
     bringing
    1.17
    Activations Density 0.122%

    No Known Activations