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

    Neuronpedia

    Jacobian LensNEW
    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. 6092
    Prev
    Next
    INDEX
    Explanations

    terms related to strategic gameplay and resource management in competitive scenarios

    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
    255
    +0.17
    0.8%
    634
    +0.10
    0.5%
    51
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.17
    0.05
    724
    +0.10
    0.05
    288
    +0.10
    0.05
    Negative Logits
     Franch
    -0.77
     Nicarag
    -0.71
     Strauss
    -0.66
    igmat
    -0.66
     Cherokee
    -0.64
     Rodham
    -0.64
     Syri
    -0.63
     Chero
    -0.63
    OSP
    -0.62
     Mock
    -0.62
    POSITIVE LOGITS
     expended
    1.28
     Gained
    1.11
     allocated
    1.07
     depletion
    1.02
     accumulated
    0.98
     expenditure
    0.96
     allotted
    0.96
     gained
    0.95
     accrued
    0.94
     invested
    0.94
    Activations Density 0.244%

    No Known Activations