© 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. 10425
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental or political accountability and misconduct

    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
    0:0.17
    1:0.02
    2:0.24
    3:0.07
    4:0.03
    5:0.07
    6:0.04
    7:0.05
    8:0.19
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
     Bok
    -3.28
    ø
    -3.23
     systemd
    -3.12
     Sapp
    -2.98
     depressive
    -2.97
    ktop
    -2.96
    vard
    -2.92
    byn
    -2.90
     psychiat
    -2.90
     Mikhail
    -2.82
    POSITIVE LOGITS
     ATF
    5.85
     Fast
    4.67
    Mex
    4.52
     Furious
    4.42
     Mexican
    4.38
    Mexico
    3.95
     cartel
    3.91
     Firearms
    3.78
     firearms
    3.74
    Fast
    3.66
    Activations Density 0.003%

    No Known Activations