© 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. 9612
    Prev
    Next
    INDEX
    Explanations

    places or scenarios where people are lined up or waiting in a queue

    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
    289
    +0.09
    0.4%
    31
    +0.09
    0.4%
    596
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.09
    0.01
    240
    +0.09
    0.01
    222
    +0.08
    0.01
    Negative Logits
    natureconservancy
    -0.79
    CVE
    -0.74
    loss
    -0.73
    effic
    -0.72
    etics
    -0.68
    ignty
    -0.67
    reck
    -0.67
     mathemat
    -0.66
    ibles
    -0.65
    BILITIES
    -0.63
    POSITIVE LOGITS
     up
    0.99
    ups
    0.91
    up
    0.84
    alled
    0.77
     shelves
    0.75
    Up
    0.74
    backer
    0.74
     Up
    0.73
     pave
    0.73
     Beir
    0.72
    Activations Density 0.031%

    No Known Activations