© 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. 363
    Prev
    Next
    INDEX
    Explanations

    references to legal authority and governmental surveillance practices

    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
    0:0.18
    1:0.03
    2:0.19
    3:0.06
    4:0.05
    5:0.09
    6:0.05
    7:0.05
    8:0.11
    9:0.05
    10:0.04
    11:0.05
    Negative Logits
    rust
    -3.04
     Cinnamon
    -2.83
     Nicola
    -2.70
    innamon
    -2.60
     buckle
    -2.58
     masc
    -2.56
     Edinburgh
    -2.50
    erek
    -2.48
    iquette
    -2.43
    rius
    -2.40
    POSITIVE LOGITS
     702
    3.62
     FISA
    3.35
     Verizon
    3.23
     upstream
    3.18
     NSA
    3.18
     Greenwald
    3.14
    osponsors
    2.94
     downstream
    2.89
     Cellular
    2.85
    NSA
    2.73
    Activations Density 0.005%

    No Known Activations