Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11274
    Prev
    Next
    INDEX
    Explanations

    references to insurgent groups and associated terrorist organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.01
    2:0.05
    3:0.50
    4:0.02
    5:0.08
    6:0.02
    7:0.03
    8:0.08
    9:0.01
    10:0.07
    11:0.02
    Negative Logits
     clarity
    -2.17
     elegance
    -2.01
     thoughtful
    -1.95
     succinct
    -1.86
     composure
    -1.83
     ceilings
    -1.82
     seating
    -1.81
     finishes
    -1.81
     weigh
    -1.79
     footing
    -1.79
    POSITIVE LOGITS
     Islamist
    3.22
     Taliban
    3.16
     terrorists
    3.08
     terrorist
    3.07
     extremist
    3.03
    terrorist
    2.99
     jihadist
    2.96
     insurgents
    2.92
     bandits
    2.87
     militant
    2.81
    Activations Density 0.960%

    No Known Activations