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. 23361
    Prev
    Next
    INDEX
    Explanations

    nutritional information and calorie content in food-related contexts

    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
    760
    +0.11
    0.5%
    524
    +0.11
    0.5%
    497
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.11
    0.03
    289
    +0.11
    0.01
    537
    +0.11
    0.03
    Negative Logits
    amera
    -0.80
    inqu
    -0.78
    Witness
    -0.75
    osures
    -0.74
    orld
    -0.74
     Parade
    -0.74
    hunt
    -0.74
     televised
    -0.73
     retrospective
    -0.73
    nesday
    -0.73
    POSITIVE LOGITS
     nutrients
    1.44
     vitamins
    1.34
     antioxidants
    1.29
     carbohydrates
    1.27
     Protein
    1.27
     protein
    1.27
     sugars
    1.26
     fats
    1.25
     enzymes
    1.25
     amino
    1.24
    Activations Density 0.187%

    No Known Activations