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 6144
    5. 8-RES_FS6144-JB
    6. 5494
    Prev
    Next
    INDEX
    Explanations

    articles related to entertainment and media news

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    109
    +0.15
    0.7%
    118
    +0.11
    0.5%
    101
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.15
    0.05
    739
    +0.11
    0.03
    679
    +0.10
    0.07
    Negative Logits
    oward
    -0.79
    SPONSORED
    -0.73
    raq
    -0.68
    crime
    -0.64
    burgh
    -0.62
    onds
    -0.62
    ails
    -0.61
    gall
    -0.60
    Woman
    -0.60
    growth
    -0.59
    POSITIVE LOGITS
     spoilers
    1.11
     excludes
    0.89
     caveats
    0.89
     Contains
    0.85
     ONLY
    0.84
     disclaim
    0.80
     assumes
    0.79
     beware
    0.78
     disclaimer
    0.78
     formatting
    0.78
    Activations Density 1.001%

    No Known Activations