© 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. 11933
    Prev
    Next
    INDEX
    Explanations

    content related to military operations and conflicts

    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
    0:0.13
    1:0.02
    2:0.19
    3:0.07
    4:0.03
    5:0.07
    6:0.04
    7:0.08
    8:0.22
    9:0.03
    10:0.03
    11:0.03
    Negative Logits
     Nicaragua
    -3.57
     Nicarag
    -3.45
     Vermont
    -3.19
    NZ
    -3.10
     Esper
    -3.08
    asio
    -2.91
    uana
    -2.77
     Duc
    -2.76
     Guatem
    -2.73
    coin
    -2.73
    POSITIVE LOGITS
     Mosul
    6.79
     Baghd
    3.89
     Raqqa
    3.83
     Daesh
    3.43
     Bakr
    3.31
     Pesh
    3.31
     Iraqi
    3.30
    Mos
    3.29
     ISIS
    3.28
    aghd
    3.27
    Activations Density 0.025%

    No Known Activations