© 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. 20350
    Prev
    Next
    INDEX
    Explanations

    phrases related to online privacy and tracking technologies

    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
    0:0.26
    1:0.02
    2:0.16
    3:0.10
    4:0.04
    5:0.07
    6:0.05
    7:0.07
    8:0.06
    9:0.04
    10:0.06
    11:0.03
    Negative Logits
     resid
    -3.44
     pont
    -2.95
     Nanto
    -2.94
     COVER
    -2.58
    Anth
    -2.56
     Anth
    -2.46
     ambulance
    -2.38
     Haz
    -2.32
     stret
    -2.31
     Mé
    -2.28
    POSITIVE LOGITS
     cookies
    5.80
     Cookies
    5.70
    Cook
    5.36
    cook
    5.33
     cookie
    4.94
     Cookie
    4.90
    cookie
    4.46
    HTTP
    3.05
     baked
    2.88
     caches
    2.83
    Activations Density 0.004%

    No Known Activations