© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 11562
    Prev
    Next
    INDEX
    Explanations

    references to political positions and individuals within government and parliamentary contexts

    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
    0:0.05
    1:0.03
    2:0.06
    3:0.14
    4:0.06
    5:0.12
    6:0.04
    7:0.08
    8:0.23
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
     rumors
    -3.55
     favor
    -3.09
     unfavorable
    -3.09
     favorable
    -3.04
     rumor
    -3.03
     honor
    -3.01
     Fresno
    -2.95
     honoring
    -2.84
     colorful
    -2.83
     neighborhood
    -2.80
    POSITIVE LOGITS
    uckland
    3.99
    Scotland
    3.87
     Fraser
    3.67
     Defence
    3.63
    Labour
    3.61
    orkshire
    3.57
     Peel
    3.56
    imet
    3.50
    aviour
    3.40
    inburgh
    3.36
    Activations Density 0.235%

    No Known Activations