© 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. 37287
    Prev
    Next
    INDEX
    Explanations

    a variety of symbols or special characters

    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
    107
    +0.10
    0.5%
    218
    +0.10
    0.5%
    103
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.10
    0.01
    103
    +0.10
    0.01
    136
    +0.09
    0.01
    Negative Logits
     board
    -0.95
    enegger
    -0.72
    ographically
    -0.71
     fabrication
    -0.69
    ulators
    -0.68
    ierrez
    -0.68
     Fargo
    -0.67
     concede
    -0.67
     cautiously
    -0.67
     charm
    -0.67
    POSITIVE LOGITS
    ¹
    1.77
    ª
    1.62
    ¨
    1.60
    £
    1.56
    Į
    1.52
    Ń
    1.52
    ¢
    1.52
    ¥
    1.51
    ±
    1.50
    º
    1.49
    Activations Density 0.002%

    No Known Activations