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 3072
    5. 8-RES_FS3072-JB
    6. 674
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical fitness and injuries

    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
    506
    +0.12
    0.5%
    393
    +0.11
    0.5%
    53
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    476
    +0.12
    0.06
    611
    +0.11
    0.08
    506
    +0.10
    0.07
    Negative Logits
    dayName
    -0.81
    maid
    -0.76
     Picks
    -0.72
    Quantity
    -0.70
    ants
    -0.65
    /-
    -0.64
     guiActive
    -0.63
     Cosponsors
    -0.62
    Ô
    -0.60
    orthy
    -0.60
    POSITIVE LOGITS
     society
    0.90
     spectrum
    0.86
     life
    0.80
    insula
    0.77
     civilization
    0.77
     globe
    0.76
     coastline
    0.75
    sembly
    0.72
     civilisation
    0.71
     humankind
    0.70
    Activations Density 0.830%

    No Known Activations