© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11004
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and public policy

    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
    393
    +0.14
    0.7%
    159
    +0.13
    0.6%
    578
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.14
    0.09
    186
    +0.13
    0.07
    578
    +0.11
    0.05
    Negative Logits
    aths
    -0.75
    tones
    -0.73
    aws
    -0.73
    amia
    -0.72
    affles
    -0.72
    ickets
    -0.72
    ARS
    -0.71
    adle
    -0.70
    oslav
    -0.70
    aughtered
    -0.70
    POSITIVE LOGITS
     phenomenon
    1.03
     discrepancy
    1.02
     culminated
    0.98
     article
    0.98
     latter
    0.95
     contrasts
    0.94
     means
    0.90
     includes
    0.90
     arrangement
    0.90
     translates
    0.89
    Activations Density 0.151%

    No Known Activations