© 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 3072
    9. 8-RES_FS3072-JB
    11. 103
    Prev
    Next
    INDEX
    Explanations

    details related to events or incidents, such as police activity, medical emergencies, or business deals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    762
    +0.11
    0.5%
    305
    +0.11
    0.5%
    337
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.11
    0.13
    724
    +0.11
    0.11
    345
    +0.11
    0.07
    Negative Logits
    oday
    -0.66
    LET
    -0.65
    utsch
    -0.65
    çīĪ
    -0.64
    aughtered
    -0.63
    aye
    -0.63
    pletion
    -0.62
    Already
    -0.62
    iyah
    -0.61
    iscons
    -0.61
    POSITIVE LOGITS
     nowadays
    1.14
     dictators
    1.00
     rarely
    0.88
     weddings
    0.84
     tends
    0.82
     seldom
    0.81
     typically
    0.81
     democracies
    0.79
     usually
    0.77
     Usually
    0.77
    Activations Density 3.196%

    No Known Activations