© 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. 10-ATT-KK
    6. 15172
    Prev
    Next
    INDEX
    Explanations

    phrases related to migration and border issues

    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
    0:0.23
    1:0.03
    2:0.04
    3:0.07
    4:0.06
    5:0.02
    6:0.05
    7:0.16
    8:0.01
    9:0.04
    10:0.19
    11:0.04
    Negative Logits
    Harris
    -3.76
     Durham
    -3.46
     Booker
    -3.17
    castle
    -3.17
     Harris
    -3.17
    Alabama
    -3.16
    Houston
    -3.14
     Yemeni
    -3.14
     Alabama
    -2.97
    wcsstore
    -2.93
    POSITIVE LOGITS
     Slov
    7.93
     Slovakia
    7.62
     Sloven
    5.58
     Slovenia
    4.97
     Slav
    4.49
     Sv
    4.13
     Czech
    4.02
     Prague
    4.01
     Macedonia
    3.96
     Yugoslav
    3.88
    Activations Density 0.003%

    No Known Activations