© 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. 22159
    Prev
    Next
    INDEX
    Explanations

    words related to circumcision and oppression

    oai_token-act-pair · gpt-4o-miniTriggered 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
    276
    +0.13
    0.6%
    549
    +0.11
    0.5%
    59
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.02
    276
    +0.11
    0.02
    85
    +0.11
    0.02
    Negative Logits
    iger
    -0.85
    aries
    -0.84
    igan
    -0.80
    ienne
    -0.79
    hips
    -0.78
    abies
    -0.77
    ism
    -0.74
    igans
    -0.72
    idad
    -0.71
    acea
    -0.69
    POSITIVE LOGITS
    vention
    0.92
    Ħ¢
    0.88
    figured
    0.88
    lesi
    0.86
    Ķ
    0.83
    stantial
    0.83
    olicy
    0.79
    ffe
    0.79
    spect
    0.78
    İĭ
    0.78
    Activations Density 0.048%

    No Known Activations