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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 548
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and economic discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    640
    +0.19
    0.9%
    314
    +0.17
    0.8%
    102
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.19
    0.14
    152
    +0.17
    0.13
    537
    +0.15
    0.12
    Negative Logits
     Dickinson
    -0.83
    ulhu
    -0.71
     Cassidy
    -0.71
     Burr
    -0.71
     Barron
    -0.71
     LW
    -0.70
     Led
    -0.69
     Loll
    -0.68
     DeV
    -0.66
     Boone
    -0.66
    POSITIVE LOGITS
    government
    1.34
    existent
    1.33
    sent
    1.25
    division
    1.22
    interest
    1.22
    dist
    1.21
    expression
    1.20
    dep
    1.20
    cont
    1.20
    development
    1.19
    Activations Density 0.715%

    No Known Activations