© 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. 19466
    Prev
    Next
    INDEX
    Explanations

    phrases indicating awareness of political figures or governance related to espionage and reassurance from authorities

    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
    0:0.19
    1:0.05
    2:0.08
    3:0.07
    4:0.04
    5:0.03
    6:0.13
    7:0.13
    8:0.02
    9:0.08
    10:0.12
    11:0.03
    Negative Logits
     Rabbi
    -3.88
    Jewish
    -3.84
     Jewish
    -3.77
     synagogue
    -3.75
     rabbi
    -3.71
    Jews
    -3.68
    adelphia
    -3.61
     Judaism
    -3.60
     Jews
    -3.49
     Torah
    -3.45
    POSITIVE LOGITS
     Rousse
    7.40
    Brazil
    4.68
     Brazil
    4.60
     Bras
    4.41
     Brazilian
    4.30
     Dil
    4.15
    ça
    4.03
    ão
    3.94
     impeachment
    3.79
    ê
    3.73
    Activations Density 0.001%

    No Known Activations