© 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. 14993
    Prev
    Next
    INDEX
    Explanations

    government and political discourse regarding nuclear policy

    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
    0:0.08
    1:0.04
    2:0.07
    3:0.04
    4:0.04
    5:0.03
    6:0.18
    7:0.05
    8:0.21
    9:0.13
    10:0.02
    11:0.05
    Negative Logits
     ACE
    -3.64
     jewelry
    -3.53
    emetery
    -3.45
     Sie
    -3.37
    Mi
    -3.24
    Ak
    -3.23
    License
    -3.20
    auga
    -3.14
    Chicago
    -3.09
    php
    -3.04
    POSITIVE LOGITS
     Rudd
    11.21
     Turnbull
    5.43
     Rasmussen
    5.07
     Swan
    5.03
     Canberra
    4.99
    Austral
    4.77
     Gill
    4.76
     Abbott
    4.64
    reens
    4.34
     Australians
    4.20
    Activations Density 0.001%

    No Known Activations