© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10815
    Prev
    Next
    INDEX
    Explanations

    connections to political figures and their actions

    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
    1:0.02
    2:0.16
    3:0.06
    4:0.03
    5:0.08
    6:0.07
    7:0.08
    8:0.18
    9:0.03
    10:0.02
    11:0.06
    Negative Logits
    nect
    -2.95
    ̶
    -2.88
     lyn
    -2.76
     baskets
    -2.75
     Ashe
    -2.75
    Node
    -2.72
     �
    -2.71
     npm
    -2.68
    annie
    -2.67
     boarded
    -2.67
    POSITIVE LOGITS
     Schwarzenegger
    7.66
    enegger
    7.08
     Terminator
    4.48
     Arnold
    4.15
     Kung
    3.48
     Expend
    3.38
     Fiorina
    3.32
     Godzilla
    3.32
     Diet
    3.29
     Celeb
    3.20
    Activations Density 0.002%

    No Known Activations