© 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. 7564
    Prev
    Next
    INDEX
    Explanations

    phrases related to combating various issues such as diseases, cyberbullying, gun violence, human trafficking, climate change, and terrorism

    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
    447
    +0.14
    0.6%
    455
    +0.11
    0.5%
    669
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.14
    0.04
    669
    +0.11
    0.04
    164
    +0.11
    0.04
    Negative Logits
    ittal
    -0.80
    felt
    -0.78
    ĸļ
    -0.77
    quartered
    -0.74
     announ
    -0.69
     tasted
    -0.67
    etry
    -0.66
    UME
    -0.66
     rubbed
    -0.66
    joice
    -0.66
    POSITIVE LOGITS
     terrorism
    1.05
     extremism
    1.05
     piracy
    1.03
     trafficking
    0.95
     corruption
    0.94
     harassment
    0.94
     discriminatory
    0.93
     racism
    0.92
     bullying
    0.91
     inequality
    0.91
    Activations Density 0.173%

    No Known Activations