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 3072
    5. 8-RES_FS3072-JB
    6. 2057
    Prev
    Next
    INDEX
    Explanations

    names of political figures and locations in East Asia

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    524
    +0.10
    0.5%
    646
    +0.10
    0.4%
    232
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.10
    232
    +0.10
    0.10
    284
    +0.10
    0.07
    Negative Logits
     msec
    -0.76
     Catalyst
    -0.71
     COVER
    -0.69
    ATTLE
    -0.66
     FedEx
    -0.65
     livest
    -0.65
    INST
    -0.64
     macros
    -0.63
     recess
    -0.63
     prescriptions
    -0.63
    POSITIVE LOGITS
    wei
    1.47
    jin
    1.33
    yu
    1.29
     Yi
    1.28
    hao
    1.28
    zhen
    1.28
     Yun
    1.25
     Ji
    1.24
     Hai
    1.23
    jiang
    1.23
    Activations Density 0.832%

    No Known Activations