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. 1347
    Prev
    Next
    INDEX
    Explanations

    information related to space exploration and scientific missions, particularly focusing on spacecraft, missions, and discoveries

    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
    434
    +0.10
    0.5%
    71
    +0.10
    0.5%
    115
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    115
    +0.10
    0.10
    109
    +0.10
    0.06
    537
    +0.10
    0.07
    Negative Logits
    geist
    -0.82
    女
    -0.80
    ç
    -0.79
     Styles
    -0.79
    conom
    -0.77
     eviction
    -0.77
    Style
    -0.77
    enfranch
    -0.76
    law
    -0.76
     Hardcore
    -0.76
    POSITIVE LOGITS
     spacecraft
    1.53
     satellites
    1.52
     orbiting
    1.38
     reconnaissance
    1.34
     unmanned
    1.30
     astronauts
    1.30
     NASA
    1.29
    NASA
    1.29
     aircraft
    1.28
     satellite
    1.25
    Activations Density 2.187%

    No Known Activations