© 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. 9-ATT-KK
    11. 23838
    Prev
    Next
    INDEX
    Explanations

    mentions of social and political tension within a specific region

    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
    0:0.10
    1:0.05
    2:0.11
    3:0.08
    4:0.05
    5:0.05
    6:0.05
    7:0.08
    8:0.25
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
     Brees
    -3.98
     NRL
    -3.39
    PLIED
    -3.37
    gerald
    -3.30
     Wellington
    -3.29
     Katrina
    -3.26
     bart
    -3.25
     sailor
    -3.11
     Dolphin
    -3.10
     Harbour
    -3.00
    POSITIVE LOGITS
     Xin
    5.86
    jiang
    5.37
     Tibet
    5.14
     Uzbek
    5.07
     Mongol
    4.88
     Tibetan
    4.60
     Kash
    4.57
     Mongolia
    4.51
     Kazakh
    4.41
     Turk
    4.34
    Activations Density 0.006%

    No Known Activations