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. 702
    Prev
    Next
    INDEX
    Explanations

    phrases related to global events and activities

    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
    393
    +0.13
    0.6%
    530
    +0.13
    0.6%
    494
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.13
    0.04
    530
    +0.13
    0.03
    362
    +0.12
    0.03
    Negative Logits
    fully
    -0.81
    ful
    -0.73
    aba
    -0.71
    PsyNetMessage
    -0.70
     Luffy
    -0.68
    vg
    -0.68
    fy
    -0.66
    tle
    -0.65
    LY
    -0.65
    fulness
    -0.64
    POSITIVE LOGITS
     globe
    1.35
     country
    1.16
     world
    1.14
     countryside
    1.05
     continent
    0.98
     nation
    0.96
     planet
    0.91
     spectrum
    0.91
     periphery
    0.90
     hemisphere
    0.89
    Activations Density 0.061%

    No Known Activations