© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 12671
    Prev
    Next
    INDEX
    Explanations

    themes related to nuclear weapons, missile tests, and international relations, particularly focusing on North Korea

    oai_token-act-pair · gpt-3.5-turbo

    references to nuclear weapons and missile tests involving North Korea

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Ward
    -0.90
    Sym
    -0.89
     Opt
    -0.83
    TOR
    -0.80
    std
    -0.80
    Merit
    -0.78
    Wisconsin
    -0.78
    Phys
    -0.78
     Aber
    -0.76
    Baltimore
    -0.76
    POSITIVE LOGITS
     Jinping
    1.03
     warheads
    0.95
    ongyang
    0.93
    arming
    0.87
    achev
    0.87
     missile
    0.86
     Laos
    0.85
     spying
    0.83
     destroyer
    0.83
     submarines
    0.83
    Activations Density 0.234%

    No Known Activations