© 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. 6974
    Prev
    Next
    INDEX
    Explanations

    data related to deaths, particularly in jails and prisons, and statistics on smoking habits and living arrangements

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    481
    +0.21
    1.0%
    241
    +0.13
    0.6%
    447
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.09
    575
    +0.13
    0.08
    481
    +0.12
    0.07
    Negative Logits
    issance
    -0.65
    issan
    -0.59
     Cadillac
    -0.56
    hiro
    -0.55
    ãĥ³ãĤ¸
    -0.54
     Seas
    -0.53
    bart
    -0.53
    ¬¼
    -0.53
     ESC
    -0.52
    illet
    -0.52
    POSITIVE LOGITS
     compared
    1.08
     apiece
    1.01
     whereas
    0.83
    Footnote
    0.81
     equivalents
    0.81
     annually
    0.75
     owing
    0.74
     during
    0.72
    *.
    0.71
     whatsoever
    0.71
    Activations Density 0.612%

    No Known Activations