© 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. 9-ATT-KK
    11. 371
    Prev
    Next
    INDEX
    Explanations

    references to government actions and related political discussions

    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
    0:0.07
    1:0.02
    2:0.11
    3:0.07
    4:0.03
    5:0.10
    6:0.03
    7:0.08
    8:0.36
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
    tsky
    -3.73
     Lv
    -3.51
     Ukrain
    -3.25
     Cavs
    -3.16
     Akron
    -3.10
     Summoner
    -3.09
     Polish
    -3.06
     Yon
    -3.06
     Bowser
    -2.98
     Ryu
    -2.98
    POSITIVE LOGITS
     Abbott
    6.38
     Canberra
    5.46
    Austral
    5.40
     Tasmania
    5.20
     Australians
    5.17
     Turnbull
    4.97
     Brisbane
    4.93
     Queensland
    4.90
    Australia
    4.82
     Australia
    4.68
    Activations Density 0.026%

    No Known Activations