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

    Neuronpedia

    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. 18596
    Prev
    Next
    INDEX
    Explanations

    references to political events, assassination attempts, and related themes

    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
    497
    +0.14
    0.7%
    288
    +0.10
    0.5%
    549
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.02
    199
    +0.10
    0.02
    414
    +0.10
    0.01
    Negative Logits
    Cola
    -0.80
    bos
    -0.77
     Refresh
    -0.73
    Ocean
    -0.72
    Va
    -0.70
    TAG
    -0.69
    Forest
    -0.69
    Loading
    -0.68
    Alpha
    -0.68
    NES
    -0.67
    POSITIVE LOGITS
     assass
    1.14
     assassination
    1.14
     assassinated
    1.10
     assassins
    1.00
     assassin
    0.99
     Assass
    0.96
     assassinate
    0.93
     slit
    0.86
     spree
    0.81
     attempt
    0.79
    Activations Density 0.041%

    No Known Activations