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. 252
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms and trends

    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
    232
    +0.14
    0.7%
    430
    +0.12
    0.6%
    373
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.13
    649
    +0.12
    0.04
    308
    +0.12
    0.07
    Negative Logits
     dart
    -0.93
     aven
    -0.82
     muster
    -0.82
    anton
    -0.78
     disg
    -0.78
     bolt
    -0.76
     gastro
    -0.76
     resent
    -0.76
     gren
    -0.75
     elves
    -0.75
    POSITIVE LOGITS
     Relationship
    1.35
     Them
    1.30
     Month
    1.30
     Away
    1.29
     Hits
    1.28
     Experience
    1.27
     Replacement
    1.26
     Problems
    1.26
     Names
    1.26
     Dates
    1.25
    Activations Density 3.159%

    No Known Activations