© 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. 5-ATT-KK
    11. 26488
    Prev
    Next
    INDEX
    Explanations

    incidents involving physical violence or assault

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.02
    2:0.04
    3:0.09
    4:0.04
    5:0.10
    6:0.03
    7:0.02
    8:0.06
    9:0.15
    10:0.18
    11:0.15
    Negative Logits
     domestically
    -1.02
     gestation
    -0.97
     premise
    -0.95
     constit
    -0.90
     Blueprint
    -0.89
     plague
    -0.88
     embargo
    -0.87
     blueprint
    -0.85
    agame
    -0.85
     ninety
    -0.83
    POSITIVE LOGITS
     Quan
    1.09
    ...]
    1.06
    EXT
    0.98
     Finally
    0.97
    rar
    0.97
    Eventually
    0.96
    CONCLUS
    0.96
    ANI
    0.95
     Asked
    0.95
    Prosecut
    0.95
    Activations Density 0.613%

    No Known Activations