© 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. 8037
    Prev
    Next
    INDEX
    Explanations

    comparisons or contrasts

    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
    684
    +0.11
    0.5%
    608
    +0.09
    0.4%
    183
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    684
    +0.11
    0.03
    183
    +0.09
    0.03
    692
    +0.09
    0.02
    Negative Logits
    bilt
    -0.78
    âĹ¼
    -0.75
     Nanto
    -0.72
    soType
    -0.70
     Warning
    -0.69
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.68
    CLASSIFIED
    -0.68
    ãĥĵ
    -0.68
    ãģ®ç
    -0.67
    interstitial
    -0.67
    POSITIVE LOGITS
     mere
    0.96
     merely
    0.90
     simply
    0.90
     superficial
    0.84
     simple
    0.79
     oneself
    0.76
     partisans
    0.73
     brute
    0.73
     aesthetics
    0.72
     cosmetic
    0.72
    Activations Density 0.105%

    No Known Activations