© 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 12288
    9. 8-RES_FS12288-JB
    11. 374
    Prev
    Next
    INDEX
    Explanations

    mentions of specific software updates or versions, especially related to Windows

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    325
    +0.12
    0.6%
    678
    +0.12
    0.5%
    606
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.12
    0.03
    594
    +0.12
    0.03
    547
    +0.10
    0.02
    Negative Logits
    iazep
    -0.77
    rahim
    -0.74
    actionDate
    -0.73
    letcher
    -0.72
    amn
    -0.72
    aez
    -0.70
    usra
    -0.68
    Bey
    -0.67
     hypot
    -0.67
    pole
    -0.67
    POSITIVE LOGITS
     kernels
    0.95
     firmware
    0.90
     Anniversary
    0.89
     tablets
    0.89
     Compatibility
    0.88
     Yosemite
    0.88
     compatibility
    0.86
     Devices
    0.86
     desktop
    0.86
     Leopard
    0.85
    Activations Density 0.136%

    No Known Activations