© 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. 8855
    Prev
    Next
    INDEX
    Explanations

    arguments and reasoning related to ethics and morality

    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
    485
    +0.10
    0.5%
    191
    +0.10
    0.4%
    246
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.10
    0.06
    485
    +0.10
    0.05
    720
    +0.09
    0.05
    Negative Logits
    OGR
    -0.73
    ActionCode
    -0.69
    Ý
    -0.68
     earthqu
    -0.68
     exting
    -0.68
    ãĤ¨ãĥ«
    -0.68
    ThumbnailImage
    -0.67
    ouble
    -0.67
    voc
    -0.67
    DeliveryDate
    -0.66
    POSITIVE LOGITS
    then
    1.15
     surely
    1.12
     why
    1.09
     then
    1.06
     THEN
    0.93
    why
    0.92
     chances
    0.87
     maybe
    0.83
     please
    0.79
     perhaps
    0.79
    Activations Density 0.181%

    No Known Activations