© 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. 8001
    Prev
    Next
    INDEX
    Explanations

    terms related to news about politics and world events, specifically focusing on controversial or sensitive topics

    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
    314
    +0.15
    0.7%
    720
    +0.13
    0.6%
    675
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.15
    0.10
    720
    +0.13
    0.10
    327
    +0.11
    0.07
    Negative Logits
     yield
    -0.73
     pyramid
    -0.69
     logger
    -0.69
     rank
    -0.67
     opportunities
    -0.65
     fortun
    -0.62
     handler
    -0.61
     jog
    -0.60
     convenience
    -0.60
     advantage
    -0.60
    POSITIVE LOGITS
    ï¸ı
    1.38
    ski
    0.95
    ï¸
    0.91
    _>
    0.91
    £
    0.90
    iversary
    0.88
    Balt
    0.88
    ews
    0.87
    capital
    0.86
    AFP
    0.83
    Activations Density 0.213%

    No Known Activations