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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1490
    Prev
    Next
    INDEX
    Explanations

    information related to whistleblowers, government leaks, and controversial organizations like WikiLeaks

    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
    447
    +0.17
    0.8%
    481
    +0.17
    0.8%
    343
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.17
    0.14
    288
    +0.17
    0.15
    346
    +0.14
    0.12
    Negative Logits
    ibus
    -0.84
    emate
    -0.84
    uns
    -0.70
    oling
    -0.69
    kees
    -0.65
    semble
    -0.65
     Pats
    -0.64
     Eminem
    -0.64
    ouver
    -0.64
    hood
    -0.64
    POSITIVE LOGITS
     Labs
    0.88
    Leaks
    0.87
     Institution
    0.79
    ®
    0.78
    MSN
    0.74
    ipedia
    0.73
     Magazine
    0.73
     Headquarters
    0.72
    ILLE
    0.72
     alumni
    0.72
    Activations Density 1.304%

    No Known Activations