© 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 49152
    9. 8-RES_FS49152-JB
    11. 37539
    Prev
    Next
    INDEX
    Explanations

    tokens related to video games or gaming terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    40
    +0.10
    0.4%
    152
    +0.10
    0.4%
    613
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.04
    701
    +0.10
    0.02
    398
    +0.09
    0.03
    Negative Logits
     respons
    -0.78
     complementary
    -0.76
     capit
    -0.70
     pac
    -0.70
     affili
    -0.70
     feder
    -0.69
     retract
    -0.68
     embargo
    -0.68
     distinguishing
    -0.68
     diplom
    -0.67
    POSITIVE LOGITS
    ricks
    0.93
    rix
    0.92
    uffs
    0.91
    eker
    0.90
    atcher
    0.88
    akery
    0.88
    utters
    0.87
    ake
    0.85
    icker
    0.85
    ix
    0.84
    Activations Density 0.060%

    No Known Activations