© 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. 16446
    Prev
    Next
    INDEX
    Explanations

    topics related to human rights violations and international law concerning Russia

    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
    0:0.15
    1:0.01
    2:0.20
    3:0.09
    4:0.03
    5:0.12
    6:0.01
    7:0.06
    8:0.16
    9:0.01
    10:0.05
    11:0.03
    Negative Logits
     Firefly
    -2.75
    lees
    -2.61
     Ange
    -2.48
     Jem
    -2.48
     Surge
    -2.42
    ||||
    -2.38
    ppo
    -2.34
    \\\\\\\\\\\\\\\\
    -2.25
     Quit
    -2.25
    UX
    -2.25
    POSITIVE LOGITS
     Sergei
    4.05
     olig
    3.13
     hockey
    3.09
     enrichment
    3.08
    ovsky
    3.01
    ikhail
    2.97
     Hockey
    2.95
     NHL
    2.86
     KGB
    2.85
     Kazakhstan
    2.84
    Activations Density 0.002%

    No Known Activations