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 49152
    5. 8-RES_FS49152-JB
    6. 41267
    Prev
    Next
    INDEX
    Explanations

    instances of the word "corruption" and related concepts

    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
    447
    +0.18
    0.9%
    288
    +0.18
    0.8%
    724
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.02
    592
    +0.18
    0.01
    263
    +0.09
    0.01
    Negative Logits
    leigh
    -0.77
    imus
    -0.74
    nee
    -0.72
     Advent
    -0.69
    lee
    -0.67
    AY
    -0.66
    eele
    -0.65
    thur
    -0.64
    nesium
    -0.64
    tz
    -0.64
    POSITIVE LOGITS
     scandals
    1.09
     perpetrated
    0.98
     corruption
    0.96
     graft
    0.87
     allegations
    0.86
    ulent
    0.85
     endemic
    0.85
     dealings
    0.84
     scandal
    0.83
     corrupt
    0.82
    Activations Density 0.021%

    No Known Activations