© 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. 6615
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    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
    604
    +0.10
    0.5%
    307
    +0.10
    0.5%
    131
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    604
    +0.10
    0.02
    131
    +0.10
    0.02
    307
    +0.10
    0.02
    Negative Logits
    chart
    -0.62
     displ
    -0.62
    imeter
    -0.59
    iche
    -0.58
    viol
    -0.58
    pract
    -0.56
    destruct
    -0.56
    infect
    -0.55
     assum
    -0.55
    conserv
    -0.55
    POSITIVE LOGITS
     sir
    1.02
     kindly
    0.96
     guys
    0.91
     gracious
    0.81
    ratulations
    0.79
    giving
    0.79
     thank
    0.78
     welcome
    0.78
     gentlemen
    0.76
    rats
    0.73
    Activations Density 0.026%

    No Known Activations