© 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. 8162
    Prev
    Next
    INDEX
    Explanations

    descriptions related to the physical attributes or characteristics of objects

    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
    712
    +0.11
    0.5%
    566
    +0.10
    0.5%
    179
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.03
    431
    +0.10
    0.02
    712
    +0.10
    0.02
    Negative Logits
     Ramadan
    -0.70
     Ank
    -0.69
     Broad
    -0.66
     Hunting
    -0.65
     Globe
    -0.65
     Aden
    -0.64
     aside
    -0.62
    amaz
    -0.61
     suggestion
    -0.60
     Fernand
    -0.59
    POSITIVE LOGITS
     destined
    0.72
     belong
    0.71
    chwitz
    0.70
    duino
    0.69
     rehears
    0.69
    Ãĥ
    0.68
    ubes
    0.68
    resso
    0.68
    iter
    0.67
     conflic
    0.67
    Activations Density 0.074%

    No Known Activations