© 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. 8672
    Prev
    Next
    INDEX
    Explanations

    statements relating to political dynamics and coalitions in Latvia

    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
    1:0.05
    2:0.04
    3:0.08
    4:0.05
    5:0.02
    6:0.04
    7:0.13
    8:0.02
    9:0.04
    10:0.20
    11:0.03
    Negative Logits
     Quan
    -3.65
     Scorpion
    -3.51
    Wan
    -3.49
     Fresno
    -3.33
     Maya
    -3.20
    asu
    -3.13
     Pharaoh
    -3.07
    araoh
    -3.05
     Xie
    -3.00
     Tulsa
    -2.96
    POSITIVE LOGITS
     Latvia
    8.90
     Lithuania
    6.42
     Lithuan
    6.35
     Lat
    5.97
    Lat
    5.83
     Baltic
    5.58
     Estonia
    5.49
     Eston
    5.40
    Balt
    4.80
     Vil
    4.72
    Activations Density 0.004%

    No Known Activations