© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 19813
    Prev
    Next
    INDEX
    Explanations

    entities related to political power and international relations

    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
    0:0.03
    1:0.01
    2:0.04
    3:0.26
    4:0.02
    5:0.07
    6:0.02
    7:0.06
    8:0.03
    9:0.01
    10:0.38
    11:0.02
    Negative Logits
     understatement
    -2.68
    hazard
    -2.16
    fail
    -2.15
     proverb
    -2.14
     Pwr
    -2.13
    impact
    -2.01
     tru
    -1.99
     anytime
    -1.93
    opsy
    -1.92
    inventoryQuantity
    -1.90
    POSITIVE LOGITS
    etsk
    3.05
     representatives
    2.62
     factions
    2.56
     parties
    2.36
     groups
    2.22
     negotiators
    2.21
     reconcil
    2.16
     entities
    2.15
    iets
    2.15
     allies
    2.12
    Activations Density 0.072%

    No Known Activations