© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15092
    Prev
    Next
    INDEX
    Explanations

    references to political leadership and specific titles within government

    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
    0:0.20
    1:0.05
    2:0.05
    3:0.06
    4:0.05
    5:0.03
    6:0.23
    7:0.09
    8:0.02
    9:0.06
    10:0.04
    11:0.06
    Negative Logits
     Cyp
    -3.36
     lobster
    -3.01
     Berm
    -2.88
     Cookie
    -2.78
    anooga
    -2.77
    atche
    -2.76
     Idaho
    -2.75
    Snow
    -2.74
     Anchorage
    -2.74
     Hayden
    -2.74
    POSITIVE LOGITS
    luaj
    4.30
    Senate
    3.88
    assian
    3.71
    rx
    3.24
    android
    3.12
     Senate
    3.08
     senate
    3.06
    utterstock
    2.90
    andro
    2.83
     Nanto
    2.82
    Activations Density 0.016%

    No Known Activations