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. 23560
    Prev
    Next
    INDEX
    Explanations

    elements related to mystery and ancient or secretive themes

    oai_token-act-pair · gpt-4o-miniTriggered 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
    362
    +0.13
    0.6%
    288
    +0.10
    0.5%
    299
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.07
    572
    +0.10
    0.06
    288
    +0.10
    0.07
    Negative Logits
    ernels
    -1.06
    Frames
    -0.97
    osponsors
    -0.97
    ometers
    -0.92
    lees
    -0.90
    urches
    -0.88
    words
    -0.88
     equivalents
    -0.88
    sites
    -0.85
    apps
    -0.85
    POSITIVE LOGITS
     batch
    1.00
     swath
    0.99
     classmate
    0.94
     colleague
    0.94
     woman
    0.89
     piece
    0.86
     plot
    0.86
     spate
    0.85
     shipment
    0.85
     pair
    0.85
    Activations Density 0.379%

    No Known Activations