© 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. 12168
    Prev
    Next
    INDEX
    Explanations

    phrases related to political opinions and actions, specifically with a focus on specific political figures or movements

    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
    55
    +0.11
    0.5%
    454
    +0.10
    0.4%
    124
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.11
    0.06
    390
    +0.10
    0.04
    584
    +0.09
    0.05
    Negative Logits
    ibli
    -0.68
     fortunes
    -0.62
    ouf
    -0.60
    angu
    -0.59
    perty
    -0.58
    ounge
    -0.56
     Hist
    -0.54
     square
    -0.53
    MORE
    -0.53
    Shift
    -0.53
    POSITIVE LOGITS
     by
    1.03
     expressly
    0.84
     during
    0.84
     jointly
    0.82
     collabor
    0.81
     pursuant
    0.80
     instituted
    0.73
     artificially
    0.72
     unanimously
    0.72
     aback
    0.69
    Activations Density 0.259%

    No Known Activations