© 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. 10-ATT-KK
    11. 21791
    Prev
    Next
    INDEX
    Explanations

    references to investigations or testimonies related to political events, particularly involving Russia and collusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.18
    1:0.03
    2:0.04
    3:0.09
    4:0.08
    5:0.02
    6:0.13
    7:0.11
    8:0.02
    9:0.05
    10:0.08
    11:0.10
    Negative Logits
     Slayer
    -3.56
     CLR
    -3.08
     Xander
    -3.02
     Surviv
    -3.00
     Luffy
    -2.97
     Wooden
    -2.91
     Rena
    -2.84
    Surv
    -2.82
     Bombay
    -2.77
     Jericho
    -2.71
    POSITIVE LOGITS
     Kislyak
    5.72
     Kremlin
    5.70
     Russia
    5.62
     Russians
    5.59
     Putin
    5.44
    Russia
    5.39
     Russian
    5.36
    Russian
    5.27
    Putin
    5.15
     Steele
    5.13
    Activations Density 0.181%

    No Known Activations