© 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. 17578
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the September 11, 2001 terrorist attacks

    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
    218
    +0.10
    0.5%
    19
    +0.10
    0.5%
    482
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    482
    +0.10
    0.03
    601
    +0.10
    0.03
    325
    +0.10
    0.03
    Negative Logits
    lishes
    -0.81
    esian
    -0.81
    UGC
    -0.79
    Fish
    -0.77
     Beard
    -0.76
    Cooldown
    -0.74
    iculture
    -0.74
    dit
    -0.73
    Lic
    -0.72
     Farmers
    -0.71
    POSITIVE LOGITS
     bombing
    1.16
    ghazi
    1.02
     bombings
    1.01
     hijacked
    1.01
     airliner
    0.93
     assassination
    0.92
     atroc
    0.90
     wreckage
    0.90
    arnaev
    0.90
     JFK
    0.89
    Activations Density 0.175%

    No Known Activations