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 3072
    5. 8-RES_FS3072-JB
    6. 2885
    Prev
    Next
    INDEX
    Explanations

    information related to safety procedures or guidelines

    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
    459
    +0.14
    0.7%
    605
    +0.12
    0.5%
    497
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.14
    0.09
    285
    +0.12
    0.06
    227
    +0.10
    0.04
    Negative Logits
    twitter
    -0.75
     Bashar
    -0.75
     Maduro
    -0.75
     Confederacy
    -0.73
     mutants
    -0.70
     presided
    -0.70
     Murdoch
    -0.70
     Plaint
    -0.69
    iannopoulos
    -0.69
     riots
    -0.69
    POSITIVE LOGITS
     beginner
    1.25
     beginners
    1.14
    Your
    1.06
    your
    1.04
     Tips
    1.02
     Helpful
    1.02
    Learn
    1.02
    Tips
    1.00
     Yourself
    0.98
     your
    0.97
    Activations Density 3.554%

    No Known Activations