© 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. 22382
    Prev
    Next
    INDEX
    Explanations

    locations and references related to Malaysia

    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
    0:0.24
    1:0.03
    2:0.04
    3:0.11
    4:0.06
    5:0.02
    6:0.06
    7:0.09
    8:0.01
    9:0.04
    10:0.19
    11:0.04
    Negative Logits
    Wisconsin
    -4.41
     Erie
    -4.22
     Milwaukee
    -4.11
     Boulder
    -3.89
     Wisconsin
    -3.81
     Wasteland
    -3.76
    Denver
    -3.62
    waukee
    -3.60
     Niagara
    -3.57
     Asheville
    -3.47
    POSITIVE LOGITS
     Malaysian
    9.51
     Malays
    9.26
     Malaysia
    9.24
     Kuala
    8.63
    Mal
    6.89
     Lumpur
    6.55
     KL
    5.71
     MH
    5.61
     Mandal
    5.54
     Indones
    5.35
    Activations Density 0.052%

    No Known Activations