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. 26235
    Prev
    Next
    INDEX
    Explanations

    phrases related to healthcare and social issues

    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
    +0.28
    1.3%
    481
    +0.23
    1.1%
    608
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.28
    0.07
    587
    +0.23
    0.06
    665
    +0.13
    0.06
    Negative Logits
    gaard
    -0.71
    thing
    -0.71
    mol
    -0.63
    owner
    -0.62
     screamed
    -0.62
    wife
    -0.62
    azz
    -0.62
    comed
    -0.61
    hari
    -0.61
     teasp
    -0.61
    POSITIVE LOGITS
     tackling
    0.98
     infrastructure
    0.93
     combating
    0.91
     improving
    0.89
     integrating
    0.88
     implementing
    0.88
     homegrown
    0.86
     manpower
    0.85
     deploying
    0.85
     developing
    0.84
    Activations Density 0.305%

    No Known Activations