© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 443
    Prev
    Next
    INDEX
    Explanations

    the word "way" in different contexts

    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
    341
    +0.10
    0.5%
    81
    +0.10
    0.5%
    50
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.10
    0.03
    50
    +0.10
    0.03
    46
    +0.10
    0.02
    Negative Logits
    cius
    -0.75
     concess
    -0.67
    arus
    -0.66
    ilts
    -0.66
    urses
    -0.63
     Fernand
    -0.62
    grave
    -0.61
    urated
    -0.61
     Kau
    -0.61
    querque
    -0.61
    POSITIVE LOGITS
    ward
    1.03
     toward
    1.02
     towards
    0.95
     onto
    0.95
     into
    0.93
     INTO
    0.90
    fare
    0.88
    é¾įåĸļ士
    0.84
    DragonMagazine
    0.81
    finder
    0.80
    Activations Density 0.089%

    No Known Activations