© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 2557
    Prev
    Next
    INDEX
    Explanations

    themes of independence and territorial issues related to Chechnya and Russia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.03
    2:0.08
    3:0.09
    4:0.04
    5:0.05
    6:0.06
    7:0.07
    8:0.34
    9:0.06
    10:0.03
    11:0.03
    Negative Logits
    uckland
    -4.94
    NZ
    -4.80
     NZ
    -4.26
     Auckland
    -4.21
     Wellington
    -3.72
     NBN
    -3.65
     Kiw
    -3.50
     Tasman
    -3.46
    Australia
    -3.39
     Palmer
    -3.37
    POSITIVE LOGITS
     Caucasus
    5.38
     Dag
    4.55
     Che
    4.46
     Baghd
    4.32
     Uzbek
    4.15
     Moscow
    4.07
     Pavel
    4.07
     Nur
    4.06
     Donetsk
    4.03
     Ily
    3.97
    Activations Density 0.006%

    No Known Activations