© 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. 14209
    Prev
    Next
    INDEX
    Explanations

    references to political coups and related terminology

    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
    0:0.16
    1:0.05
    2:0.03
    3:0.06
    4:0.07
    5:0.03
    6:0.13
    7:0.19
    8:0.02
    9:0.08
    10:0.06
    11:0.07
    Negative Logits
     riders
    -2.57
     Schw
    -2.53
     coaster
    -2.52
     racer
    -2.44
     Bike
    -2.42
     FANTASY
    -2.42
     cyclists
    -2.40
    idth
    -2.40
     sunscreen
    -2.39
     Fenrir
    -2.38
    POSITIVE LOGITS
     coup
    4.65
     overthrow
    3.74
     Coup
    3.60
     overth
    3.52
     Maduro
    3.25
     treason
    3.25
     Gaddafi
    3.15
     topple
    3.05
     Maid
    2.99
     democratically
    2.96
    Activations Density 0.012%

    No Known Activations