© 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. 2-ATT-KK
    11. 23374
    Prev
    Next
    INDEX
    Explanations

    information related to political conflicts in the Middle East, particularly involving Turkey, Syria, Iraq, and Kurdish forces

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    1:0.04
    2:0.20
    3:0.07
    4:0.12
    5:0.06
    6:0.04
    7:0.04
    8:0.04
    9:0.17
    10:0.07
    11:0.03
    Negative Logits
    idious
    -1.74
    ulative
    -1.26
    umatic
    -1.22
    oyer
    -1.20
     FANTASY
    -1.19
    oidal
    -1.17
    itely
    -1.17
     mercury
    -1.16
    umers
    -1.12
     horm
    -1.11
    POSITIVE LOGITS
    ween
    1.32
     separatists
    1.30
    Army
    1.29
    istan
    1.28
     rebels
    1.22
    Reb
    1.21
    Fu
    1.19
    Fighting
    1.19
     Islands
    1.19
     factions
    1.19
    Activations Density 0.015%

    No Known Activations