© 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. 8827
    Prev
    Next
    INDEX
    Explanations

    information related to computer hardware specifications and user reviews

    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
    373
    +0.14
    0.6%
    661
    +0.10
    0.4%
    277
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.14
    0.04
    397
    +0.10
    0.03
    640
    +0.09
    0.05
    Negative Logits
     satir
    -0.88
    bleacher
    -0.86
     conject
    -0.75
     combatants
    -0.72
     Aster
    -0.72
     rhetorical
    -0.71
     subter
    -0.71
     Jazeera
    -0.69
     obfusc
    -0.68
     Summoner
    -0.67
    POSITIVE LOGITS
    Rated
    1.15
     Defin
    0.97
     LOVE
    0.94
     Bought
    0.92
    etsy
    0.91
    Customer
    0.89
    LO
    0.87
    expensive
    0.85
     Review
    0.85
     Bulk
    0.85
    Activations Density 0.392%

    No Known Activations