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. 747
    Prev
    Next
    INDEX
    Explanations

    information related to criminal activities, investigations, and legal proceedings

    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
    295
    +0.10
    0.5%
    599
    +0.10
    0.5%
    760
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.10
    0.11
    630
    +0.10
    0.09
    295
    +0.10
    0.08
    Negative Logits
     idiots
    -0.75
    enario
    -0.74
    acceptable
    -0.72
    upid
    -0.71
    bugs
    -0.70
     fools
    -0.70
    ria
    -0.70
    react
    -0.70
    BIP
    -0.69
     correctness
    -0.69
    POSITIVE LOGITS
     stint
    1.30
     specializing
    1.06
     founding
    1.01
     graduated
    0.96
     extensively
    0.95
     toured
    0.94
     exce
    0.93
     fluent
    0.92
     Married
    0.91
     freelance
    0.90
    Activations Density 4.742%

    No Known Activations