© 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. 41547
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly focusing on their significance or roles in various contexts

    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
    339
    +0.13
    0.6%
    430
    +0.10
    0.4%
    332
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.01
    257
    +0.10
    0.00
    1
    +0.10
    0.01
    Negative Logits
    ierrez
    -0.80
    inals
    -0.77
    IBLE
    -0.71
    ered
    -0.68
    anamo
    -0.67
    sen
    -0.67
    cens
    -0.67
    CLASSIFIED
    -0.67
    raltar
    -0.65
    sburgh
    -0.63
    POSITIVE LOGITS
    oke
    0.86
    ju
    0.85
    usha
    0.84
    emon
    0.83
    uba
    0.76
     Scotia
    0.76
    ilee
    0.74
    ét
    0.73
    jac
    0.73
    ppa
    0.71
    Activations Density 0.002%

    No Known Activations