© 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. 5-ATT-KK
    11. 2595
    Prev
    Next
    INDEX
    Explanations

    specific references to uranium and plutonium in the context of nuclear energy and weapons development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.05
    3:0.05
    4:0.06
    5:0.05
    6:0.07
    7:0.09
    8:0.02
    9:0.10
    10:0.32
    11:0.09
    Negative Logits
     satir
    -1.54
     Celebr
    -1.54
    iquette
    -1.47
     Macy
    -1.47
    cele
    -1.45
     celebrate
    -1.44
     celebrating
    -1.42
    �
    -1.41
    黒
    -1.36
     landmarks
    -1.35
    POSITIVE LOGITS
     uranium
    1.74
    utonium
    1.65
     plutonium
    1.47
    IFIED
    1.41
     residues
    1.37
     deposition
    1.34
     phosphate
    1.29
    alyst
    1.27
     precursor
    1.26
     oxide
    1.25
    Activations Density 0.008%

    No Known Activations