© 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. 10-ATT-KK
    11. 14965
    Prev
    Next
    INDEX
    Explanations

    references to political events and figures, particularly related to terrorism and security in Pakistan

    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
    0:0.38
    1:0.03
    2:0.05
    3:0.06
    4:0.08
    5:0.03
    6:0.04
    7:0.07
    8:0.02
    9:0.05
    10:0.07
    11:0.06
    Negative Logits
     Pelicans
    -4.17
    ovych
    -4.07
     Saturn
    -4.04
     Ole
    -3.98
     Knox
    -3.82
     Ukrainians
    -3.72
     Ukrainian
    -3.60
     Greek
    -3.56
     Sony
    -3.51
     Vader
    -3.45
    POSITIVE LOGITS
    Pakistan
    6.98
     Pakistani
    6.69
     Islamabad
    6.61
     Karachi
    6.56
     Pakistan
    6.32
     Imran
    5.66
     Sharif
    5.65
    Pak
    5.38
    ullah
    5.23
     Mush
    5.16
    Activations Density 0.040%

    No Known Activations