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 49152
    5. 8-RES_FS49152-JB
    6. 43406
    Prev
    Next
    INDEX
    Explanations

    references to exposure and related health effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    608
    +0.12
    0.6%
    489
    +0.10
    0.5%
    634
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.12
    0.02
    601
    +0.10
    0.01
    634
    +0.10
    0.01
    Negative Logits
    widget
    -0.94
    yssey
    -0.76
    iture
    -0.72
    NES
    -0.72
    roy
    -0.69
    tenance
    -0.69
    wise
    -0.68
    Tracker
    -0.68
    Reviewed
    -0.67
    aurus
    -0.67
    POSITIVE LOGITS
     sunlight
    1.02
     radiation
    0.96
     danger
    0.93
     contaminated
    0.89
     contaminants
    0.85
     firsthand
    0.84
     gunfire
    0.83
     ridicule
    0.82
     mist
    0.79
     contamination
    0.79
    Activations Density 0.028%

    No Known Activations