© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 10812
    Prev
    Next
    INDEX
    Explanations

    references to military operations and strategies related to ISIL and the Kurdish forces

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.17
    1:0.03
    2:0.24
    3:0.06
    4:0.06
    5:0.02
    6:0.05
    7:0.13
    8:0.02
    9:0.04
    10:0.09
    11:0.04
    Negative Logits
     Bee
    -2.78
     Serial
    -2.76
     Actress
    -2.71
    anta
    -2.68
     Bots
    -2.67
     Carpenter
    -2.63
     Macy
    -2.58
     Apollo
    -2.58
     Methodist
    -2.52
     Bunny
    -2.51
    POSITIVE LOGITS
     ISIL
    8.68
     PKK
    3.75
     Daesh
    3.71
     Kurdish
    3.59
     Kurd
    3.51
     Raqqa
    3.48
    Nusra
    3.47
     Syrians
    3.47
     Kurds
    3.44
    ISIS
    3.44
    Activations Density 0.009%

    No Known Activations