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. 512
    Prev
    Next
    INDEX
    Explanations

    government-related terms and proper nouns related to government entities

    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
    159
    +0.14
    0.6%
    23
    +0.10
    0.4%
    754
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    590
    +0.14
    0.02
    23
    +0.10
    0.03
    145
    +0.10
    0.03
    Negative Logits
     Leilan
    -0.69
     Halls
    -0.66
    schild
    -0.65
     Sidd
    -0.62
     backward
    -0.61
     Referred
    -0.61
    theless
    -0.61
     bottleneck
    -0.59
    BACK
    -0.59
     administrative
    -0.59
    POSITIVE LOGITS
    .,
    1.45
    .?
    1.11
    ./
    1.10
    .:
    1.07
    ubs
    1.06
    .;
    1.05
    .),
    1.02
    nyder
    1.01
    .,"
    0.95
    awar
    0.94
    Activations Density 0.055%

    No Known Activations