© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 12051
    Prev
    Next
    INDEX
    Explanations

    phrases or patterns related to specific languages or nationalities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.11
    1:0.09
    2:0.06
    3:0.03
    4:0.02
    5:0.02
    6:0.20
    7:0.13
    8:0.02
    9:0.03
    10:0.20
    11:0.04
    Negative Logits
    DOM
    -2.91
    س
    -2.90
    illard
    -2.81
    mble
    -2.81
    dar
    -2.75
    ulk
    -2.69
    arson
    -2.59
     Hag
    -2.52
    FU
    -2.50
     Advent
    -2.49
    POSITIVE LOGITS
     Pol
    9.47
    Pol
    7.96
     pol
    7.22
     POL
    5.92
    pol
    5.91
    POL
    5.05
     Polish
    4.70
     Poles
    4.27
     Polo
    4.22
     Poland
    4.17
    Activations Density 0.020%

    No Known Activations