© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23908
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their roles in competitive fighting events

    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
    430
    +0.10
    0.5%
    389
    +0.10
    0.5%
    427
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.10
    0.05
    346
    +0.10
    0.03
    180
    +0.10
    0.03
    Negative Logits
     UNCLASSIFIED
    -0.93
     Gutenberg
    -0.86
    sonian
    -0.85
    âĹ¼
    -0.85
    minecraft
    -0.83
    ItemTracker
    -0.81
    Newsletter
    -0.78
    aceae
    -0.78
     Cthulhu
    -0.77
    gencies
    -0.77
    POSITIVE LOGITS
     MMA
    1.41
     rematch
    1.29
     UFC
    1.22
    UFC
    1.22
     bout
    1.17
     wrestler
    1.15
     knockout
    1.09
     steroid
    1.08
     opponent
    1.07
     matchup
    1.07
    Activations Density 0.390%

    No Known Activations