© 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. 19525
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflicts and responsibilities within a community or organization

    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
    481
    +0.17
    0.8%
    462
    +0.10
    0.5%
    717
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.17
    0.07
    608
    +0.10
    0.07
    705
    +0.09
    0.05
    Negative Logits
     proverb
    -0.75
     seldom
    -0.73
     ingenious
    -0.70
    iom
    -0.67
     marvelous
    -0.67
     fascinating
    -0.66
     rarely
    -0.66
     surprisingly
    -0.65
     ain
    -0.64
     doubtless
    -0.64
    POSITIVE LOGITS
     anymore
    1.36
     nor
    1.07
     any
    0.89
     anything
    0.86
     anytime
    0.74
     anybody
    0.69
     anyone
    0.66
     whatsoever
    0.64
     wrongdoing
    0.61
    etz
    0.60
    Activations Density 0.836%

    No Known Activations