© 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 24576
    9. 8-RES_FS24576-JB
    11. 1298
    Prev
    Next
    INDEX
    Explanations

    words related to spatial description in structures or features, potentially related to architecture or machinery

    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
    481
    +0.14
    0.6%
    173
    +0.12
    0.5%
    756
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.14
    0.05
    49
    +0.12
    0.05
    486
    +0.11
    0.03
    Negative Logits
    é¾įå¥ij士
    -0.93
    ģĸ
    -0.71
    pires
    -0.67
    roo
    -0.67
    ourke
    -0.65
    atever
    -0.64
    STD
    -0.63
    olean
    -0.62
     Thou
    -0.62
    eur
    -0.62
    POSITIVE LOGITS
     themselves
    1.33
     individually
    0.96
     collectively
    0.95
    selves
    0.89
     uniformly
    0.89
     numbered
    0.88
     evenly
    0.83
     scattered
    0.78
     dispersed
    0.77
     rotated
    0.74
    Activations Density 0.538%

    No Known Activations