© 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. 9-ATT-KK
    11. 18595
    Prev
    Next
    INDEX
    Explanations

    references to incidents involving Gaza

    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
    0:0.17
    1:0.02
    2:0.18
    3:0.07
    4:0.03
    5:0.08
    6:0.04
    7:0.06
    8:0.24
    9:0.02
    10:0.02
    11:0.03
    Negative Logits
     Bigfoot
    -3.56
    Wisconsin
    -3.41
    Ohio
    -3.40
    Madison
    -3.35
    Florida
    -3.23
     samurai
    -3.17
    cius
    -3.12
     Saskatchewan
    -3.09
     Columbus
    -3.05
     Cincinnati
    -3.02
    POSITIVE LOGITS
     Gaza
    6.58
    Gaza
    6.22
     Hamas
    6.18
     Gaz
    5.01
     Palestinian
    4.60
     Palestinians
    4.49
     IDF
    4.26
     Strip
    4.22
    Palest
    4.18
     Raf
    4.15
    Activations Density 0.097%

    No Known Activations