© 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. 10-ATT-KK
    11. 15570
    Prev
    Next
    INDEX
    Explanations

    instances of geographic or political references related to Kerala and its officials

    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
    0:0.14
    1:0.05
    2:0.05
    3:0.10
    4:0.05
    5:0.02
    6:0.10
    7:0.10
    8:0.03
    9:0.04
    10:0.23
    11:0.04
    Negative Logits
    izzard
    -3.39
    ETF
    -3.34
    zinski
    -3.31
    Weiss
    -3.20
     GA
    -3.17
    querque
    -3.12
     Hydra
    -3.09
    phia
    -3.08
     PHI
    -3.03
     Dempsey
    -3.00
    POSITIVE LOGITS
     Kerala
    7.13
    erala
    4.59
     Ern
    4.49
     Koz
    3.96
     Laksh
    3.94
     Tamil
    3.92
     Mal
    3.72
     Karn
    3.48
     mal
    3.44
     Bengal
    3.43
    Activations Density 0.003%

    No Known Activations