© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14088
    Prev
    Next
    INDEX
    Explanations

    references to terrorist activities and their impact

    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
    0:0.32
    1:0.06
    2:0.06
    3:0.06
    4:0.06
    5:0.04
    6:0.06
    7:0.06
    8:0.02
    9:0.05
    10:0.11
    11:0.04
    Negative Logits
     Cuban
    -3.57
     Cuba
    -3.54
     Icelandic
    -3.48
     Havana
    -3.46
     Russians
    -3.40
     Tibet
    -3.33
     Iceland
    -3.33
     Poles
    -3.31
     Cub
    -3.30
     Ulster
    -3.30
    POSITIVE LOGITS
     Boko
    4.10
     Nigerian
    3.91
     Nigeria
    3.80
     Niger
    3.52
    ophe
    3.50
     Maid
    3.20
    javascript
    3.18
    ascript
    3.04
     JavaScript
    2.98
    illard
    2.93
    Activations Density 0.005%

    No Known Activations