© 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. 20793
    Prev
    Next
    INDEX
    Explanations

    keywords related to discussion and improvement of economic conditions

    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
    0:0.26
    1:0.07
    2:0.06
    3:0.04
    4:0.03
    5:0.03
    6:0.07
    7:0.15
    8:0.01
    9:0.04
    10:0.15
    11:0.03
    Negative Logits
     Planes
    -3.19
     Airbus
    -2.95
     Hawks
    -2.91
    rael
    -2.90
     Indones
    -2.85
     Blackhawks
    -2.80
     Pau
    -2.80
     Mush
    -2.78
    RAW
    -2.77
     Fuji
    -2.73
    POSITIVE LOGITS
     Bridgewater
    9.56
     Teddy
    4.84
     Zimmer
    4.70
     Vikings
    4.54
    Minnesota
    3.94
     Bradford
    3.94
     Minnesota
    3.27
     Lyme
    3.24
    natureconservancy
    3.08
     Stef
    3.03
    Activations Density 0.001%

    No Known Activations