© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 10940
    Prev
    Next
    INDEX
    Explanations

    references to airplanes or aircraft

    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
    537
    +0.12
    0.5%
    288
    +0.11
    0.5%
    741
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.12
    0.02
    652
    +0.11
    0.01
    741
    +0.10
    0.01
    Negative Logits
    ãģį
    -0.70
    女
    -0.68
    UGC
    -0.68
    FINE
    -0.66
    å¦
    -0.66
    Interstitial
    -0.65
    ãĤ±
    -0.65
     Bened
    -0.65
     Tablet
    -0.64
     CoC
    -0.64
    POSITIVE LOGITS
    liner
    1.50
    liners
    1.29
    ting
    1.03
     airliner
    1.02
    fare
    0.99
     jets
    0.95
    planes
    0.95
     flown
    0.94
    ted
    0.92
    pack
    0.92
    Activations Density 0.017%

    No Known Activations