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. 453
    Prev
    Next
    INDEX
    Explanations

    information related to transportation and accidents, with a focus on issues concerning air travel

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    288
    +0.15
    0.7%
    32
    +0.12
    0.6%
    1
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    32
    +0.15
    0.02
    575
    +0.12
    0.02
    75
    +0.10
    0.02
    Negative Logits
    arios
    -0.71
    enegger
    -0.69
    ritz
    -0.65
    ologies
    -0.65
     Skydragon
    -0.64
    SOURCE
    -0.63
    OLOGY
    -0.63
     Tate
    -0.62
    eanor
    -0.62
     Retrieved
    -0.60
    POSITIVE LOGITS
     onboard
    0.99
     passenger
    0.96
     passengers
    0.95
     pige
    0.92
     cabin
    0.91
     pigeon
    0.88
    wings
    0.85
    engers
    0.85
     flights
    0.84
    iences
    0.84
    Activations Density 0.021%

    No Known Activations