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. 2648
    Prev
    Next
    INDEX
    Explanations

    statistics and information related to sports players and their performances

    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
    17
    +0.10
    0.4%
    150
    +0.10
    0.4%
    260
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.10
    0.11
    283
    +0.10
    0.04
    150
    +0.10
    0.06
    Negative Logits
    dayName
    -0.76
    assetsadobe
    -0.70
    SpaceEngineers
    -0.68
    irie
    -0.68
    insula
    -0.66
    ESE
    -0.65
    Į
    -0.65
    igraph
    -0.64
    ¬¼
    -0.64
    imil
    -0.64
    POSITIVE LOGITS
     totaling
    1.13
     counting
    1.05
     six
    1.03
     seven
    1.01
     nine
    0.96
     eight
    0.95
     132
    0.93
     thirteen
    0.92
     five
    0.92
     fourteen
    0.92
    Activations Density 1.668%

    No Known Activations