© 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. 45588
    Prev
    Next
    INDEX
    Explanations

    references to Indigenous and Aboriginal peoples and 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
    288
    +0.15
    0.7%
    481
    +0.15
    0.7%
    496
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.15
    0.01
    755
    +0.15
    0.01
    496
    +0.13
    0.01
    Negative Logits
    advertising
    -0.80
    ysis
    -0.78
    ueller
    -0.77
    abl
    -0.76
    fare
    -0.74
    oldemort
    -0.73
    witz
    -0.73
    arnaev
    -0.71
    iral
    -0.71
    igslist
    -0.71
    POSITIVE LOGITS
     Peoples
    1.10
     Communities
    0.94
     peoples
    0.92
     communities
    0.92
     Affairs
    0.84
    apolis
    0.84
     Australians
    0.83
     Nations
    0.81
     tribes
    0.81
     Territories
    0.80
    Activations Density 0.006%

    No Known Activations