© 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. 19389
    Prev
    Next
    INDEX
    Explanations

    instances of expressions regarding effort, thought, research, energy, and work

    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
    13
    +0.12
    0.5%
    65
    +0.10
    0.4%
    459
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    13
    +0.12
    0.04
    408
    +0.10
    0.04
    344
    +0.10
    0.04
    Negative Logits
    tis
    -0.70
    ģ«
    -0.69
     sung
    -0.66
    EStream
    -0.65
     outnumbered
    -0.62
     Supported
    -0.60
     erupt
    -0.60
    Ĥİ
    -0.58
     uploading
    -0.58
     chant
    -0.57
    POSITIVE LOGITS
     emphasis
    1.10
     blame
    0.95
     attention
    0.84
     groundwork
    0.84
     resources
    0.79
     pressure
    0.73
     burdens
    0.72
     caution
    0.72
    pressure
    0.71
     onto
    0.70
    Activations Density 0.127%

    No Known Activations