© 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. 8733
    Prev
    Next
    INDEX
    Explanations

    phrases describing specific actions or events

    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
    447
    +0.35
    1.8%
    480
    +0.20
    1.0%
    481
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.35
    0.06
    480
    +0.20
    0.02
    464
    +0.17
    0.07
    Negative Logits
     Vaugh
    -0.77
    oppable
    -0.73
    enegger
    -0.68
     Seym
    -0.67
    cffff
    -0.60
    erenn
    -0.60
     shenan
    -0.59
     Nieto
    -0.59
    GBT
    -0.58
     Jagu
    -0.57
    POSITIVE LOGITS
    malink
    0.64
     english
    0.60
    join
    0.55
    CLOSE
    0.51
    ĻĤ
    0.51
    variable
    0.51
     thumbnail
    0.51
    cius
    0.50
    ?]
    0.49
     huh
    0.49
    Activations Density 0.390%

    No Known Activations