© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 9092
    Prev
    Next
    INDEX
    Explanations

    references to officials and statements from government leaders, particularly in a defense context

    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
    0:0.16
    1:0.02
    2:0.35
    3:0.08
    4:0.04
    5:0.06
    6:0.03
    7:0.05
    8:0.08
    9:0.02
    10:0.03
    11:0.02
    Negative Logits
    nect
    -2.90
     Lyft
    -2.88
    flows
    -2.79
     hospitality
    -2.75
     Taxi
    -2.73
     Speedway
    -2.73
     tourism
    -2.71
     traders
    -2.69
     taxis
    -2.66
     Nost
    -2.64
    POSITIVE LOGITS
    Defense
    5.28
    defense
    4.64
     defence
    4.30
     defense
    4.28
     Defense
    4.21
     Defence
    3.95
     defenses
    3.88
     DEFENSE
    3.87
    戦
    3.62
     defences
    3.54
    Activations Density 0.025%

    No Known Activations