© 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. 10-ATT-KK
    11. 16857
    Prev
    Next
    INDEX
    Explanations

    references to political leaders and major decisions affecting Iraq

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.38
    1:0.02
    2:0.03
    3:0.09
    4:0.06
    5:0.02
    6:0.05
    7:0.11
    8:0.01
    9:0.04
    10:0.07
    11:0.04
    Negative Logits
     Wilde
    -4.17
     Luigi
    -4.11
     bunny
    -4.04
     Wu
    -3.83
     Cuomo
    -3.82
     MTA
    -3.63
     Macy
    -3.59
     Cic
    -3.58
     Giovanni
    -3.58
     Moto
    -3.52
    POSITIVE LOGITS
     Iraqis
    9.16
     Baghdad
    8.75
     Iraqi
    8.71
    Iraq
    8.54
     Iraq
    7.81
     Saddam
    7.77
     Mosul
    6.58
     Kurdistan
    6.36
     Sunni
    6.22
     Shiite
    6.18
    Activations Density 0.195%

    No Known Activations