© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 20806
    Prev
    Next
    INDEX
    Explanations

    references to events involving tragedy and loss of life, specifically in the context of a nightclub incident

    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
    0:0.29
    1:0.03
    2:0.03
    3:0.06
    4:0.06
    5:0.04
    6:0.12
    7:0.13
    8:0.02
    9:0.05
    10:0.05
    11:0.06
    Negative Logits
     irrigation
    -4.16
     wheat
    -3.80
     Manit
    -3.77
     rover
    -3.74
     Wheat
    -3.67
    Whe
    -3.62
     Agricultural
    -3.51
     maize
    -3.48
     potatoes
    -3.40
     drought
    -3.36
    POSITIVE LOGITS
     nightclub
    6.11
     Pulse
    5.13
     DJs
    4.26
     Diaz
    4.24
     boun
    4.13
     Wyn
    4.07
     Mate
    4.01
    club
    4.00
     bartender
    3.94
    DJ
    3.79
    Activations Density 0.004%

    No Known Activations