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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 2180
    Prev
    Next
    INDEX
    Explanations

    information related to aviation incidents and flights

    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
    269
    +0.12
    0.5%
    733
    +0.10
    0.5%
    512
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.09
    346
    +0.10
    0.07
    326
    +0.10
    0.07
    Negative Logits
     Cumber
    -0.89
    ãĥ¤
    -0.75
    acity
    -0.73
    FINE
    -0.72
    essee
    -0.72
    女
    -0.69
     Coke
    -0.67
     Territories
    -0.66
    uther
    -0.63
    Scotland
    -0.63
    POSITIVE LOGITS
     Flight
    1.05
    plane
    0.99
     hangar
    0.99
    wings
    0.98
    planes
    0.97
     flights
    0.97
     jets
    0.95
     flown
    0.95
     flight
    0.95
     flying
    0.93
    Activations Density 0.838%

    No Known Activations