© 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. 415
    Prev
    Next
    INDEX
    Explanations

    references to government officials and institutions

    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
    0:0.09
    1:0.01
    2:0.07
    3:0.06
    4:0.03
    5:0.05
    6:0.09
    7:0.03
    8:0.39
    9:0.09
    10:0.02
    11:0.03
    Negative Logits
     Miliband
    -4.74
     Chilean
    -4.45
     Ö
    -4.30
     Icelandic
    -4.29
     Copenhagen
    -4.28
     Danish
    -4.22
     Iceland
    -4.09
     Denmark
    -3.88
     Canary
    -3.86
     Malays
    -3.81
    POSITIVE LOGITS
    Indiana
    8.85
     Indiana
    8.53
     Indianapolis
    7.63
     Indy
    6.95
     IU
    6.15
     Purdue
    5.92
     Blooming
    5.29
     Colts
    5.13
     Pacers
    5.03
     Pence
    4.92
    Activations Density 0.038%

    No Known Activations