© 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. 9874
    Prev
    Next
    INDEX
    Explanations

    words related to political entities and events related to Pakistan

    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
    481
    +0.19
    0.9%
    288
    +0.17
    0.8%
    447
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.19
    0.03
    288
    +0.17
    0.03
    458
    +0.12
    0.03
    Negative Logits
    mble
    -0.72
    umbnails
    -0.69
    aunder
    -0.69
    llo
    -0.66
     Merrill
    -0.66
     Lys
    -0.66
     Bucc
    -0.64
    yson
    -0.61
    llan
    -0.58
    iencies
    -0.58
    POSITIVE LOGITS
    istani
    1.54
    abad
    0.95
    istan
    0.95
    awar
    0.90
    Pakistan
    0.83
     Sharif
    0.83
     Taliban
    0.81
    pour
    0.80
     Karachi
    0.78
     Pakistan
    0.76
    Activations Density 0.051%

    No Known Activations