© 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. 703
    Prev
    Next
    INDEX
    Explanations

    information related to performing arts events and entertainment activities

    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
    73
    +0.12
    0.5%
    496
    +0.10
    0.5%
    175
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    73
    +0.12
    0.07
    546
    +0.10
    0.06
    43
    +0.10
    0.05
    Negative Logits
    iple
    -0.80
    olo
    -0.74
    Previous
    -0.73
    zel
    -0.72
    oÄŁan
    -0.72
    uce
    -0.70
    igl
    -0.70
    enz
    -0.68
    lde
    -0.67
    rou
    -0.67
    POSITIVE LOGITS
     namely
    1.39
     albeit
    1.02
     which
    0.95
     Spectre
    0.85
     viz
    0.84
     consisting
    0.82
     dubbed
    0.77
     aptly
    0.76
     although
    0.76
    which
    0.75
    Activations Density 0.394%

    No Known Activations