© 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 49152
    9. 8-RES_FS49152-JB
    11. 41581
    Prev
    Next
    INDEX
    Explanations

    phrases that bring attention to social and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    71
    +0.12
    0.5%
    672
    +0.10
    0.4%
    498
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.12
    0.03
    362
    +0.10
    0.03
    669
    +0.09
    0.02
    Negative Logits
    --+
    -0.78
    fork
    -0.77
    ée
    -0.72
    Iterator
    -0.69
    NING
    -0.69
    beam
    -0.69
    tails
    -0.67
    andowski
    -0.66
    ulla
    -0.66
    pour
    -0.66
    POSITIVE LOGITS
     injust
    1.02
     dangers
    0.92
     shortcomings
    0.88
     misogyny
    0.88
     atrocities
    0.87
     wrongdoing
    0.87
     homosexuality
    0.87
     abuses
    0.87
     issues
    0.86
     sexism
    0.83
    Activations Density 0.119%

    No Known Activations