© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15373
    Prev
    Next
    INDEX
    Explanations

    references to uranium and nuclear deals or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.22
    1:0.08
    2:0.05
    3:0.06
    4:0.05
    5:0.02
    6:0.11
    7:0.15
    8:0.02
    9:0.04
    10:0.10
    11:0.05
    Negative Logits
    ijn
    -3.68
     Hebdo
    -3.30
    ussen
    -3.11
     Luther
    -3.11
    ieval
    -3.05
     Tanz
    -2.99
     Polk
    -2.84
     Riley
    -2.77
    odox
    -2.77
     preach
    -2.76
    POSITIVE LOGITS
     Uran
    7.66
     uranium
    7.33
     plutonium
    4.62
     Kazakhstan
    4.39
     Kazakh
    4.27
     Nuclear
    4.24
     reactors
    4.14
     centrif
    3.94
     reactor
    3.83
     nuclear
    3.83
    Activations Density 0.012%

    No Known Activations