© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 12287
    Prev
    Next
    INDEX
    Explanations

    discussions about consumer demand and competition in the context of gaming

    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
    1:0.13
    2:0.08
    3:0.04
    4:0.03
    5:0.04
    6:0.04
    7:0.11
    8:0.02
    9:0.07
    10:0.20
    11:0.04
    Negative Logits
     burg
    -2.92
    Lib
    -2.79
     sed
    -2.73
    Pet
    -2.72
     dup
    -2.69
     Libyan
    -2.67
     Bin
    -2.66
     bin
    -2.60
     Kro
    -2.58
    Ly
    -2.52
    POSITIVE LOGITS
     Yosh
    8.15
     Yoshi
    5.05
     Tosh
    5.00
     Nish
    4.73
     Hirosh
    4.42
     Ish
    4.08
     Kats
    3.87
     Yamato
    3.77
     Yam
    3.76
     Yah
    3.73
    Activations Density 0.001%

    No Known Activations