© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10518
    Prev
    Next
    INDEX
    Explanations

    references to user privacy and security in messaging applications

    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
    0:0.20
    1:0.02
    2:0.14
    3:0.05
    4:0.03
    5:0.07
    6:0.10
    7:0.06
    8:0.08
    9:0.14
    10:0.03
    11:0.02
    Negative Logits
     CRC
    -3.38
     loader
    -3.34
     Valiant
    -3.05
     BAT
    -3.00
     redevelopment
    -2.90
    aterasu
    -2.89
     Toro
    -2.87
     Rebirth
    -2.86
     Luthor
    -2.85
     Liver
    -2.84
    POSITIVE LOGITS
     Skype
    9.06
    Chat
    5.10
     WhatsApp
    5.00
     chat
    4.77
     Chat
    4.72
     Messenger
    4.70
    Sky
    4.39
     messaging
    4.34
     chats
    4.34
    chat
    4.34
    Activations Density 0.010%

    No Known Activations