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. 8440
    Prev
    Next
    INDEX
    Explanations

    references to toxic substances, hazardous chemicals, and health risks in products, particularly plastics

    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
    59
    +0.14
    0.6%
    167
    +0.11
    0.5%
    455
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.14
    0.02
    455
    +0.11
    0.03
    730
    +0.10
    0.02
    Negative Logits
    doms
    -0.94
     Sabha
    -0.83
    lag
    -0.71
    straight
    -0.68
     athlet
    -0.68
    laus
    -0.65
    urai
    -0.63
    jab
    -0.62
    Sport
    -0.62
     Carney
    -0.61
    POSITIVE LOGITS
     enough
    0.81
     sufficient
    0.79
     traces
    0.79
     lots
    0.78
     provisions
    0.77
     spoilers
    0.75
     plenty
    0.73
    ãĥĸ
    0.73
    ãĤ£
    0.72
     snippets
    0.72
    Activations Density 0.048%

    No Known Activations