© 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 1536
    9. 8-RES_FS1536-JB
    11. 1050
    Prev
    Next
    INDEX
    Explanations

    keywords related to political news and current 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_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    125
    +0.12
    0.5%
    170
    +0.10
    0.5%
    551
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.12
    0.14
    724
    +0.10
    0.15
    665
    +0.10
    0.15
    Negative Logits
    ortment
    -0.78
    ochond
    -0.69
    weeney
    -0.68
    arlane
    -0.67
    akin
    -0.65
    inia
    -0.64
    odan
    -0.62
    eatured
    -0.61
    umbn
    -0.61
    ĪĴ
    -0.60
    POSITIVE LOGITS
    .
    0.89
    .–
    0.86
    .—
    0.86
    .;
    0.80
    .--
    0.79
    .",
    0.77
    ;
    0.76
    .(
    0.76
    \.
    0.74
     because
    0.74
    Activations Density 3.892%

    No Known Activations