© 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 49152
    9. 8-RES_FS49152-JB
    11. 41716
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mack."

    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
    101
    +0.12
    0.5%
    659
    +0.11
    0.5%
    232
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.01
    232
    +0.11
    0.01
    53
    +0.11
    0.01
    Negative Logits
    é»Ĵ
    -0.77
    âĸ¬
    -0.74
    issance
    -0.68
     eclipse
    -0.67
    =-=-=-=-=-=-=-=-
    -0.66
     revolving
    -0.65
    é¾įå¥ij士
    -0.65
    0000000000000000
    -0.62
    ORED
    -0.62
    ++++++++
    -0.61
    POSITIVE LOGITS
    enzie
    1.77
    intosh
    1.67
    innon
    1.25
    lin
    1.00
    hews
    1.00
    onse
    0.99
    downs
    0.97
    ham
    0.96
    lins
    0.92
    down
    0.92
    Activations Density 0.002%

    No Known Activations