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

    Neuronpedia

    APICircuit 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. 811
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and political themes, particularly related to the Founding Fathers of the United States

    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
    7
    +0.11
    0.5%
    756
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    598
    +0.11
    0.05
    390
    +0.11
    0.05
    443
    +0.10
    0.06
    Negative Logits
    ebin
    -0.93
     blocker
    -0.91
    aspx
    -0.85
     referral
    -0.79
    Alert
    -0.79
     blockers
    -0.78
     waiver
    -0.78
    Recommend
    -0.78
    Quality
    -0.77
    parency
    -0.75
    POSITIVE LOGITS
     Era
    1.33
     era
    1.31
     civilizations
    1.20
     1912
    1.19
     centuries
    1.18
     eras
    1.18
     historians
    1.17
     1914
    1.16
     1910
    1.16
     historian
    1.16
    Activations Density 5.529%

    No Known Activations