© 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. 8834
    Prev
    Next
    INDEX
    Explanations

    phrases that reference statements, rulings, or announcements regarding specific events or individuals

    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
    0:0.15
    1:0.11
    2:0.06
    3:0.03
    4:0.03
    5:0.03
    6:0.08
    7:0.13
    8:0.02
    9:0.05
    10:0.20
    11:0.03
    Negative Logits
     Pelicans
    -3.00
    Rocket
    -2.98
     Morty
    -2.80
    orb
    -2.77
     RL
    -2.76
     Rocket
    -2.76
     Orbital
    -2.63
     Parables
    -2.57
    ateurs
    -2.55
     LO
    -2.55
    POSITIVE LOGITS
     Tak
    7.70
     Wak
    4.62
     Nak
    4.55
     Sak
    4.12
     Miy
    4.01
     Fuk
    3.88
     Tsuk
    3.84
    Tok
    3.83
     Aki
    3.83
     Tik
    3.78
    Activations Density 0.004%

    No Known Activations