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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 655
    Prev
    Next
    INDEX
    Explanations

    keywords related to genetics, genes, mutations, and neurological processes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    516
    +0.14
    0.6%
    99
    +0.14
    0.6%
    223
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.15
    516
    +0.14
    0.10
    575
    +0.11
    0.11
    Negative Logits
    taboola
    -0.84
     Nights
    -0.83
    grounds
    -0.79
    aneers
    -0.77
    ground
    -0.77
    Weather
    -0.74
    ership
    -0.72
    isconsin
    -0.72
     Christy
    -0.71
    ivia
    -0.70
    POSITIVE LOGITS
     molecule
    1.16
     molecules
    1.13
     enzymes
    1.11
     proteins
    1.09
     genes
    1.07
     membranes
    1.06
     cells
    1.05
     membrane
    1.05
     biomark
    1.01
     enzyme
    1.01
    Activations Density 2.169%

    No Known Activations