© 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. 5206
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a relationship between different entities, particularly in the context of business or cultural exchanges

    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
    1:0.03
    2:0.05
    3:0.04
    4:0.06
    5:0.04
    6:0.19
    7:0.04
    8:0.10
    9:0.27
    10:0.02
    11:0.04
    Negative Logits
     caches
    -3.35
     Bran
    -3.34
     burner
    -3.33
     pyramid
    -3.31
     Gibbs
    -3.29
     Echoes
    -3.28
     Alexandria
    -3.25
     Gle
    -3.22
    lar
    -3.22
     banner
    -3.18
    POSITIVE LOGITS
     Japan
    7.69
    Japan
    7.52
     Japanese
    7.00
    Japanese
    6.95
     Tokyo
    6.67
    Tok
    6.33
     Fuji
    5.99
     Fuk
    5.95
     Yosh
    5.86
     Tsuk
    5.57
    Activations Density 0.012%

    No Known Activations