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 24576
    5. 8-RES_FS24576-JB
    6. 23465
    Prev
    Next
    INDEX
    Explanations

    mentions of project updates and development progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    756
    +0.13
    0.6%
    723
    +0.12
    0.6%
    459
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    723
    +0.13
    0.06
    665
    +0.12
    0.06
    641
    +0.11
    0.06
    Negative Logits
    SPONSORED
    -0.92
    cigarettes
    -0.86
     Adolf
    -0.85
     Saddam
    -0.82
    Jews
    -0.79
    toggle
    -0.79
    uphem
    -0.76
     Koran
    -0.76
     Kissinger
    -0.75
     Cheney
    -0.75
    POSITIVE LOGITS
     Kickstarter
    1.21
     Patreon
    1.20
     ourselves
    0.96
     deadlines
    0.90
     demo
    0.89
     independ
    0.89
     devs
    0.88
     prototypes
    0.88
     updates
    0.88
     crowdfunding
    0.87
    Activations Density 0.946%

    No Known Activations