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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 13614
    Prev
    Next
    INDEX
    Explanations

    references to political leaders and their actions related to governance, particularly in the context of anti-terrorism

    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
    0:0.13
    1:0.05
    2:0.05
    3:0.10
    4:0.15
    5:0.03
    6:0.10
    7:0.08
    8:0.03
    9:0.06
    10:0.07
    11:0.09
    Negative Logits
     Islamist
    -4.64
     Mohammed
    -4.56
     Islamists
    -4.50
     jihad
    -4.44
     Mohammad
    -4.40
     Saudi
    -4.31
     Sheikh
    -4.30
     Riyadh
    -4.20
     Iranian
    -4.05
     Sunni
    -4.01
    POSITIVE LOGITS
    byss
    3.56
    natureconservancy
    3.25
    paio
    3.05
    Pokémon
    2.99
    �
    2.77
    emouth
    2.74
    �
    2.74
     Poke
    2.73
    @#&
    2.72
    parser
    2.71
    Activations Density 0.002%

    No Known Activations