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. 745
    Prev
    Next
    INDEX
    Explanations

    Roman numerals for Super Bowl games

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    649
    +0.14
    0.6%
    650
    +0.11
    0.5%
    383
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.01
    649
    +0.11
    0.01
    208
    +0.11
    0.01
    Negative Logits
    âĸ¬
    -0.91
    keeping
    -0.84
    flies
    -0.80
    zai
    -0.80
    actionDate
    -0.79
    à©
    -0.78
     behavi
    -0.76
    âĸ¬âĸ¬
    -0.74
     è£ıç
    -0.74
    Ú
    -0.73
    POSITIVE LOGITS
    VII
    1.26
    III
    1.22
    II
    1.09
    VI
    1.05
    IX
    0.96
    avier
    0.90
    XL
    0.86
    xus
    0.85
    IV
    0.85
    uggage
    0.83
    Activations Density 0.019%

    No Known Activations