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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 10210
    Prev
    Next
    INDEX
    Explanations

    statements related to political conflicts and military operations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    480
    +0.54
    2.9%
    266
    +0.12
    0.6%
    447
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.54
    0.01
    266
    +0.12
    0.14
    385
    +0.11
    0.09
    Negative Logits
     Edison
    -0.75
     Whitney
    -0.70
     Everett
    -0.70
     Nerd
    -0.68
     Courtney
    -0.68
    Denver
    -0.68
     dime
    -0.68
     Darrell
    -0.68
     Vaughn
    -0.68
     Briggs
    -0.67
    POSITIVE LOGITS
     Rohingya
    1.21
    zbollah
    1.17
     Kurdish
    1.14
     Houth
    1.14
     PKK
    1.11
     Islamist
    1.10
     Hezbollah
    1.09
     YPG
    1.09
     Syrian
    1.09
     militants
    1.08
    Activations Density 2.507%

    No Known Activations