© 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 12288
    9. 8-RES_FS12288-JB
    11. 9561
    Prev
    Next
    INDEX
    Explanations

    words related to historical references, specifically focusing on the themes of slavery and labor exploitation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    288
    +0.14
    0.7%
    447
    +0.12
    0.6%
    350
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.03
    639
    +0.12
    0.02
    350
    +0.11
    0.02
    Negative Logits
    atche
    -0.82
    frames
    -0.73
    INC
    -0.73
    bsp
    -0.71
    20439
    -0.68
    ãĤ¡
    -0.67
    atform
    -0.66
     antioxid
    -0.65
    Downloadha
    -0.65
     Editors
    -0.64
    POSITIVE LOGITS
     slaves
    1.06
     slave
    1.03
     plantation
    1.02
     slavery
    1.00
    vag
    0.92
     plantations
    0.86
     Leia
    0.86
     labor
    0.85
     enslaved
    0.84
    maid
    0.84
    Activations Density 0.096%

    No Known Activations