© 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 EvalsExportsinterp-engineNEWAPI 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. 22874
    Prev
    Next
    INDEX
    Explanations

    information related to Donald Trump's actions and statements

    oai_token-act-pair · gpt-4o-miniTriggered 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
    430
    +0.11
    0.5%
    546
    +0.11
    0.5%
    203
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.11
    0.05
    55
    +0.11
    0.06
    741
    +0.10
    0.04
    Negative Logits
     convent
    -0.79
     Sisters
    -0.78
     Seraph
    -0.71
     Mages
    -0.70
     NAD
    -0.70
     membranes
    -0.68
     Closed
    -0.67
    REL
    -0.67
     Canary
    -0.66
     specialization
    -0.65
    POSITIVE LOGITS
     pard
    0.99
     pardon
    0.94
     veto
    0.94
    Putin
    0.86
     impuls
    0.86
     appoint
    0.86
    realDonaldTrump
    0.82
     Jr
    0.81
     tweeting
    0.81
     retweet
    0.80
    Activations Density 0.516%

    No Known Activations