© 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. 20483
    Prev
    Next
    INDEX
    Explanations

    information related to prominent political figures and their connections

    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
    1:0.05
    2:0.07
    3:0.05
    4:0.05
    5:0.02
    6:0.16
    7:0.16
    8:0.01
    9:0.04
    10:0.11
    11:0.05
    Negative Logits
    byss
    -3.50
     LM
    -2.89
    elaide
    -2.68
     Ada
    -2.65
     Punk
    -2.63
     Prometheus
    -2.53
     worms
    -2.51
     Subaru
    -2.50
     beetles
    -2.49
     runners
    -2.37
    POSITIVE LOGITS
     Kushner
    7.36
     Jared
    5.53
     Ivanka
    5.02
    Iv
    3.94
     Kislyak
    3.61
     Kush
    3.25
    arov
    3.24
     Rosenstein
    3.17
     Manafort
    3.16
     Bannon
    3.13
    Activations Density 0.012%

    No Known Activations