© 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. 11071
    Prev
    Next
    INDEX
    Explanations

    mentions of political events and governmental 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
    0:0.06
    1:0.01
    2:0.10
    3:0.10
    4:0.03
    5:0.08
    6:0.03
    7:0.06
    8:0.40
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
    Utah
    -4.37
     Arkansas
    -4.22
     Louisiana
    -3.94
     Utah
    -3.82
     Mississ
    -3.57
     Sioux
    -3.49
     Tyson
    -3.48
     Hawaiian
    -3.41
     coral
    -3.34
    Salt
    -3.32
    POSITIVE LOGITS
     Bundes
    7.63
     Merkel
    6.99
     German
    6.52
    Germany
    6.41
     Cologne
    6.37
     Germans
    6.35
     Berlin
    6.22
     Germany
    6.10
    German
    6.07
     Bundesliga
    6.07
    Activations Density 0.154%

    No Known Activations