Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1243
    Prev
    Next
    INDEX
    Explanations

    political and governmental terms and actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    +0.15
    0.7%
    484
    +0.11
    0.5%
    150
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.15
    0.15
    0
    +0.11
    0.14
    393
    +0.11
    0.15
    Negative Logits
    meric
    -0.85
    DragonMagazine
    -0.75
    onica
    -0.74
    agger
    -0.73
    uta
    -0.71
    actionDate
    -0.70
    ieg
    -0.70
    pees
    -0.69
    lot
    -0.67
    meet
    -0.67
    POSITIVE LOGITS
     hence
    1.51
     thus
    1.50
     thereby
    1.48
     consequently
    1.44
     therefore
    1.31
     secondly
    1.25
     thence
    1.17
     subsequently
    1.11
     furthermore
    1.10
     vice
    1.10
    Activations Density 1.388%

    No Known Activations