© 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. 21853
    Prev
    Next
    INDEX
    Explanations

    sentences that express caution or warnings

    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
    0:0.08
    1:0.02
    2:0.06
    3:0.03
    4:0.05
    5:0.02
    6:0.32
    7:0.04
    8:0.10
    9:0.17
    10:0.02
    11:0.02
    Negative Logits
     Newport
    -4.26
    LAN
    -3.98
    entin
    -3.97
     Irvine
    -3.96
     Rogue
    -3.96
     Leica
    -3.83
     Wolfe
    -3.72
     Huawei
    -3.72
     Wilkinson
    -3.70
     LAN
    -3.66
    POSITIVE LOGITS
     Bab
    10.68
     bab
    6.40
     Baby
    5.20
    baby
    5.07
    Baby
    4.94
     babies
    4.84
     Nab
    4.77
     infants
    4.68
     baby
    4.62
     Bib
    4.59
    Activations Density 0.005%

    No Known Activations