Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 768
    5. 8-RES_FS768-JB
    6. 308
    Prev
    Next
    INDEX
    Explanations

    recipe instructions, particularly for cooking savory dishes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    678
    +0.12
    0.5%
    545
    +0.11
    0.5%
    390
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.12
    0.12
    545
    +0.11
    0.08
    390
    +0.10
    0.07
    Negative Logits
     Gamergate
    -0.86
    href
    -0.84
     interoper
    -0.73
    udicrous
    -0.70
     headlined
    -0.69
     patrols
    -0.68
     careers
    -0.67
    Privacy
    -0.66
    Politics
    -0.66
     academ
    -0.66
    POSITIVE LOGITS
    Ingredients
    1.50
     roasted
    1.31
     Ingredients
    1.30
     baking
    1.29
     yeast
    1.28
     dried
    1.28
     garlic
    1.25
     coconut
    1.24
     veggies
    1.23
     butter
    1.23
    Activations Density 4.159%

    No Known Activations