© 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 12288
    9. 8-RES_FS12288-JB
    11. 1858
    Prev
    Next
    INDEX
    Explanations

    references to Shakespearean characters and organizations or leaders related to philanthropy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    651
    +0.12
    0.6%
    151
    +0.11
    0.5%
    497
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.06
    326
    +0.11
    0.04
    151
    +0.11
    0.04
    Negative Logits
    essler
    -0.66
     Marathon
    -0.63
    packing
    -0.61
    RT
    -0.60
    lif
    -0.60
    ©¶æ
    -0.55
     Dynam
    -0.55
    aternity
    -0.55
     Typhoon
    -0.54
     LCS
    -0.54
    POSITIVE LOGITS
    ous
    1.25
    hip
    1.25
    ary
    1.14
    ess
    1.03
    ante
    0.96
    orship
    0.95
    hips
    0.94
    ial
    0.93
    arial
    0.90
    antes
    0.89
    Activations Density 0.261%

    No Known Activations