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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22868
    Prev
    Next
    INDEX
    Explanations

    references to political and military actions in specific countries

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to conflicts and military actions in Iraq and Syria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.09
    2:0.06
    3:0.09
    4:0.04
    5:0.07
    6:0.04
    7:0.06
    8:0.06
    9:0.19
    10:0.12
    11:0.05
    Negative Logits
     FANTASY
    -1.47
    Cra
    -1.41
     promotions
    -1.39
     advertisements
    -1.39
     warranties
    -1.35
     vinyl
    -1.31
     antioxid
    -1.27
    ancies
    -1.26
     yarn
    -1.26
     cosmetics
    -1.23
    POSITIVE LOGITS
    merga
    1.87
     Nato
    1.69
     Hezbollah
    1.59
     Turks
    1.57
     ravaged
    1.56
    istan
    1.56
     Shiite
    1.55
     Lavrov
    1.53
    zbollah
    1.52
     NATO
    1.52
    Activations Density 0.192%

    No Known Activations