© 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. 9-ATT-KK
    11. 6626
    Prev
    Next
    INDEX
    Explanations

    mentions of ISIS and related Islamic terrorist activities or groups

    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
    0:0.32
    1:0.01
    2:0.08
    3:0.10
    4:0.03
    5:0.11
    6:0.01
    7:0.06
    8:0.14
    9:0.01
    10:0.04
    11:0.02
    Negative Logits
     ANC
    -2.80
     Marlins
    -2.79
     Huawei
    -2.73
     Morse
    -2.69
     Gupta
    -2.63
     Chandra
    -2.51
     Yamaha
    -2.49
     Nixon
    -2.45
     Suzuki
    -2.41
     Bernstein
    -2.41
    POSITIVE LOGITS
     caliphate
    2.89
     Raqqa
    2.70
    aghd
    2.46
    qqa
    2.41
    upload
    2.38
    robat
    2.38
     Baghd
    2.37
     ISIS
    2.36
    ISIS
    2.35
    GET
    2.27
    Activations Density 0.047%

    No Known Activations