© 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. 9-ATT-KK
    11. 17202
    Prev
    Next
    INDEX
    Explanations

    instances of violence and human rights abuses against civilians

    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
    0:0.07
    1:0.01
    2:0.11
    3:0.19
    4:0.02
    5:0.23
    6:0.02
    7:0.08
    8:0.06
    9:0.01
    10:0.10
    11:0.03
    Negative Logits
    torn
    -2.54
     catastrophe
    -2.27
    hazard
    -2.26
     disaster
    -2.24
     trap
    -2.17
    hower
    -2.15
     nightmare
    -2.13
     hazard
    -2.11
     warr
    -2.10
     trauma
    -2.09
    POSITIVE LOGITS
     Christians
    2.56
     Churches
    2.49
     Hindus
    2.47
    Jews
    2.32
     Jews
    2.31
     Catholics
    2.22
     mosques
    2.18
     ASUS
    2.18
     Armen
    2.15
    Jewish
    2.15
    Activations Density 0.213%

    No Known Activations