© 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 49152
    9. 8-RES_FS49152-JB
    11. 43069
    Prev
    Next
    INDEX
    Explanations

    phrases related to nationalism and the idea of making America great again

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    2
    +0.13
    0.6%
    517
    +0.10
    0.4%
    75
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.13
    0.01
    567
    +0.10
    0.01
    152
    +0.09
    0.02
    Negative Logits
    legged
    -0.76
    etics
    -0.74
     intervals
    -0.68
     fluids
    -0.67
    ances
    -0.67
    requent
    -0.66
     eyebrows
    -0.66
     externalToEVAOnly
    -0.65
    tones
    -0.64
    phrine
    -0.64
    POSITIVE LOGITS
     Airl
    0.88
     Forever
    0.85
     liv
    0.83
     Again
    0.77
     Murd
    0.76
     Beautiful
    0.73
     2025
    0.73
     Manufacturing
    0.73
     AMERICA
    0.73
     prosperous
    0.71
    Activations Density 0.035%

    No Known Activations