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. 11746
    Prev
    Next
    INDEX
    Explanations

    references to Politico, a political news organization

    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
    592
    +0.10
    0.5%
    288
    +0.10
    0.5%
    271
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.10
    0.02
    475
    +0.10
    0.01
    346
    +0.10
    0.01
    Negative Logits
    ĸļ
    -0.87
    alogue
    -0.76
    isted
    -0.73
    oji
    -0.72
    perse
    -0.71
    ysis
    -0.70
    lights
    -0.69
     WWF
    -0.69
    igned
    -0.69
    oki
    -0.67
    POSITIVE LOGITS
     Magazine
    1.04
     Caucus
    0.99
     Heights
    0.81
     Politics
    0.80
     Insider
    0.79
    Politics
    0.76
     Correspond
    0.74
    OPLE
    0.73
     aide
    0.72
     Digest
    0.71
    Activations Density 0.017%

    No Known Activations