© 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. 13125
    Prev
    Next
    INDEX
    Explanations

    specific names and places associated with cultural or historical significance

    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
    0:0.22
    1:0.17
    2:0.02
    3:0.04
    4:0.03
    5:0.02
    6:0.07
    7:0.07
    8:0.03
    9:0.03
    10:0.17
    11:0.06
    Negative Logits
     Roku
    -4.42
     Chero
    -3.83
     Uzbek
    -3.42
     Iro
    -3.40
     Hos
    -3.33
     Cherokee
    -3.28
     Philippine
    -3.26
     Memphis
    -3.25
     Baton
    -3.23
     Shia
    -3.23
    POSITIVE LOGITS
    ß
    4.35
    liga
    4.27
     Reich
    4.20
     Bundesliga
    4.19
    ologne
    4.18
    rieg
    4.18
    Sch
    4.11
    ische
    4.07
    wagen
    4.02
    ollen
    4.00
    Activations Density 0.073%

    No Known Activations