Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19264
    Prev
    Next
    INDEX
    Explanations

    references to sports events, teams, and competition

    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
    650
    +0.11
    0.5%
    417
    +0.10
    0.5%
    537
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    650
    +0.11
    0.02
    422
    +0.10
    0.02
    116
    +0.09
    0.02
    Negative Logits
    terday
    -0.85
    ku
    -0.84
    ð
    -0.84
    nels
    -0.82
    metic
    -0.80
    paio
    -0.77
    fm
    -0.74
    fil
    -0.74
    enegger
    -0.73
    wik
    -0.72
    POSITIVE LOGITS
     standings
    1.36
     Finals
    1.22
     playoff
    1.12
     Championship
    1.11
     Championships
    1.10
     playoffs
    1.10
     championship
    1.09
     semifinals
    1.06
     Playoffs
    1.05
     Playoff
    1.03
    Activations Density 0.035%

    No Known Activations