© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 16975
    Prev
    Next
    INDEX
    Explanations

    specific terms related to nuclear weapons and security issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.03
    2:0.04
    3:0.37
    4:0.05
    5:0.11
    6:0.07
    7:0.02
    8:0.02
    9:0.07
    10:0.07
    11:0.03
    Negative Logits
     interviewer
    -2.55
    iquette
    -2.52
    anship
    -2.25
    aution
    -2.17
    Management
    -2.11
     etiquette
    -2.10
    lihood
    -2.05
     surgeon
    -2.03
     promoter
    -2.00
    ategory
    -1.99
    POSITIVE LOGITS
     originals
    2.42
    pieces
    2.27
     ones
    2.23
    uggets
    2.15
    aceous
    2.03
     copies
    2.01
     versions
    2.00
     pieces
    1.98
    usable
    1.95
     cylinders
    1.95
    Activations Density 0.907%

    No Known Activations