© 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. 8107
    Prev
    Next
    INDEX
    Explanations

    topics related to social issues

    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
    480
    +0.47
    2.5%
    87
    +0.22
    1.2%
    447
    +0.18
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.47
    0.09
    480
    +0.22
    0.03
    288
    +0.18
    0.11
    Negative Logits
    enegger
    -0.77
    ONSORED
    -0.65
    abwe
    -0.62
    ornings
    -0.61
    renheit
    -0.60
    itored
    -0.59
     tradem
    -0.58
    Lago
    -0.57
    \\\\\\\\
    -0.57
     conclud
    -0.55
    POSITIVE LOGITS
    iest
    0.87
     portion
    0.79
     aspect
    0.74
     fallacy
    0.74
     element
    0.73
     hypothesis
    0.71
    liest
    0.71
     axis
    0.70
     process
    0.68
    osphere
    0.65
    Activations Density 0.702%

    No Known Activations