© 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. 7274
    Prev
    Next
    INDEX
    Explanations

    references to legal frameworks or proceedings related to international law

    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
    0:0.14
    1:0.03
    2:0.14
    3:0.07
    4:0.04
    5:0.07
    6:0.09
    7:0.08
    8:0.16
    9:0.06
    10:0.04
    11:0.04
    Negative Logits
    ◼
    -3.89
     Kyl
    -3.40
    Disney
    -3.07
    �
    -3.07
    ―
    -3.00
     glim
    -2.87
     Grimm
    -2.87
    使
    -2.82
    Transform
    -2.80
     Sora
    -2.75
    POSITIVE LOGITS
     ICC
    6.88
     Cricket
    6.25
     BCC
    6.24
     cricket
    5.96
    Pakistan
    5.04
     Pakistan
    4.89
     Islamabad
    4.66
     bats
    4.54
     Pakistani
    4.27
    bats
    4.10
    Activations Density 0.012%

    No Known Activations