© 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 24576
    9. 8-RES_FS24576-JB
    11. 19346
    Prev
    Next
    INDEX
    Explanations

    mentions of different countries in news articles

    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
    +0.19
    0.9%
    288
    +0.11
    0.5%
    447
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    672
    +0.19
    0.02
    601
    +0.11
    0.02
    481
    +0.09
    0.02
    Negative Logits
    uggest
    -0.73
    DERR
    -0.73
     Velocity
    -0.72
    urations
    -0.72
    eport
    -0.70
    ocry
    -0.69
    inventoryQuantity
    -0.69
    wered
    -0.68
    helle
    -0.68
    LEASE
    -0.67
    POSITIVE LOGITS
    wide
    1.45
    men
    0.99
    oslov
    0.83
    ESE
    0.82
     illegally
    0.81
    side
    0.81
     annexed
    0.80
    liness
    0.79
    manship
    0.77
    's
    0.76
    Activations Density 0.051%

    No Known Activations