© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10850
    Prev
    Next
    INDEX
    Explanations

    phrases concerning international relations 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
    0:0.06
    1:0.02
    2:0.06
    3:0.04
    4:0.06
    5:0.04
    6:0.26
    7:0.05
    8:0.10
    9:0.19
    10:0.02
    11:0.04
    Negative Logits
     Weld
    -4.30
     Spectre
    -3.77
    hend
    -3.56
     Witt
    -3.31
    veland
    -3.31
    Bell
    -3.28
     weld
    -3.27
    Denver
    -3.26
     Brewery
    -3.15
     dispensary
    -3.14
    POSITIVE LOGITS
     Africans
    8.28
     Africa
    8.21
     Nigeria
    7.24
    African
    7.17
     Ethiop
    6.88
     Nigerian
    6.73
     Ghana
    6.65
     Uganda
    6.65
     Kenya
    6.56
     Ethiopia
    6.51
    Activations Density 0.024%

    No Known Activations