© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14920
    Prev
    Next
    INDEX
    Explanations

    information related to legal rulings and implications

    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
    0:0.16
    1:0.07
    2:0.07
    3:0.05
    4:0.06
    5:0.04
    6:0.14
    7:0.10
    8:0.03
    9:0.05
    10:0.13
    11:0.04
    Negative Logits
     Beng
    -2.85
     Sach
    -2.72
     Mew
    -2.68
     Esports
    -2.67
     Grimm
    -2.61
     MMR
    -2.54
     dem
    -2.52
     Nid
    -2.48
     ASD
    -2.48
    imore
    -2.45
    POSITIVE LOGITS
     Costco
    8.70
     shoppers
    3.40
     Warehouse
    3.29
     warehouses
    3.26
     warehouse
    3.25
     UPS
    3.22
     Staples
    3.15
     Trader
    3.07
    amazon
    3.04
    Cost
    3.03
    Activations Density 0.002%

    No Known Activations