Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 46114
    Prev
    Next
    INDEX
    Explanations

    mentions of the Suez Canal and associated names

    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
    7
    +0.10
    0.5%
    152
    +0.10
    0.5%
    494
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.01
    224
    +0.10
    0.01
    316
    +0.10
    0.01
    Negative Logits
    ramer
    -0.80
    ovember
    -0.77
    unders
    -0.71
    Ħ¢
    -0.71
    OPS
    -0.70
    sonian
    -0.69
    ften
    -0.68
    Īè
    -0.68
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
    oway
    -0.67
    POSITIVE LOGITS
    alez
    0.94
    rez
    0.84
    quez
    0.82
    vous
    0.82
    uala
    0.81
     Canal
    0.81
     Marina
    0.78
    ional
    0.76
    ón
    0.76
    lez
    0.75
    Activations Density 0.010%

    No Known Activations