© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37174
    Prev
    Next
    INDEX
    Explanations

    game modes and gameplay mechanics in video games

    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
    650
    +0.10
    0.5%
    398
    +0.10
    0.5%
    600
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.10
    0.01
    650
    +0.10
    0.01
    767
    +0.09
    0.01
    Negative Logits
    folk
    -0.64
     ultras
    -0.62
    gling
    -0.61
    ogy
    -0.59
    alg
    -0.58
    mong
    -0.58
    soDeliveryDate
    -0.57
    æĿ
    -0.55
    expr
    -0.55
    uple
    -0.54
    POSITIVE LOGITS
     Controller
    0.73
     Powered
    0.72
     Mode
    0.70
    allery
    0.70
     ÃĹ
    0.68
     Content
    0.66
     Oops
    0.65
    UTERS
    0.63
    perture
    0.62
     SHARES
    0.62
    Activations Density 0.003%

    No Known Activations