© 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. 14865
    Prev
    Next
    INDEX
    Explanations

    phrases related to business operations and technological innovations

    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
    0:0.13
    1:0.09
    2:0.08
    3:0.06
    4:0.05
    5:0.03
    6:0.10
    7:0.10
    8:0.03
    9:0.05
    10:0.17
    11:0.05
    Negative Logits
    hyde
    -3.47
     HERO
    -3.16
    Hom
    -3.00
    obos
    -2.99
     Gn
    -2.96
     foll
    -2.88
    helm
    -2.79
     Emacs
    -2.72
    ayne
    -2.72
     glim
    -2.59
    POSITIVE LOGITS
     Tata
    9.13
     Mumbai
    3.97
     Taj
    3.86
     Bangalore
    3.78
     Maharashtra
    3.68
     Tamil
    3.65
    India
    3.52
     Takeru
    3.46
     Bombay
    3.46
     India
    3.45
    Activations Density 0.004%

    No Known Activations