© 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. 9-ATT-KK
    11. 327
    Prev
    Next
    INDEX
    Explanations

    phrases related to military strategies and historical contexts

    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
    2:0.16
    3:0.09
    4:0.04
    5:0.07
    6:0.05
    7:0.12
    8:0.22
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
     Parish
    -3.65
     parish
    -3.06
     worsh
    -3.03
     cous
    -2.95
     Cabrera
    -2.94
     Orleans
    -2.92
     wors
    -2.90
     Jindal
    -2.87
     Osiris
    -2.84
     Corinth
    -2.83
    POSITIVE LOGITS
     Cold
    5.20
    Soviet
    4.76
    Cold
    4.73
     Baltic
    4.53
     Soviet
    4.35
     Soviets
    4.28
     KGB
    4.13
    cold
    4.04
     USSR
    3.91
     Belarus
    3.88
    Activations Density 0.002%

    No Known Activations