© 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. 6814
    Prev
    Next
    INDEX
    Explanations

    phrases related to terrorism and its impact on society

    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
    0:0.30
    1:0.04
    2:0.03
    3:0.06
    4:0.04
    5:0.01
    6:0.05
    7:0.13
    8:0.01
    9:0.03
    10:0.21
    11:0.04
    Negative Logits
    ��
    -3.51
    Miller
    -3.38
    Colorado
    -3.21
    Hamilton
    -3.16
     Canadiens
    -3.12
    Seattle
    -3.08
     Colorado
    -3.08
     Haas
    -3.06
     Carpenter
    -2.97
    icago
    -2.96
    POSITIVE LOGITS
     Nigeria
    9.13
     Nigerian
    9.01
     Boko
    8.06
     Niger
    7.70
     Cameroon
    6.11
     Lag
    5.98
     Ghana
    5.08
     Senegal
    4.73
     Yor
    4.48
     Mb
    4.45
    Activations Density 0.018%

    No Known Activations