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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 13761
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding encryption and its implications for privacy and freedom of expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.19
    1:0.08
    2:0.11
    3:0.03
    4:0.02
    5:0.02
    6:0.06
    7:0.14
    8:0.01
    9:0.04
    10:0.21
    11:0.04
    Negative Logits
    黒
    -3.34
    Detroit
    -2.95
    incinn
    -2.81
     Chili
    -2.73
    UTF
    -2.61
     Detroit
    -2.60
     Scorp
    -2.54
     Dust
    -2.52
    Graph
    -2.50
     Dresden
    -2.50
    POSITIVE LOGITS
     Kay
    8.57
    Kay
    8.23
     kay
    6.75
    kay
    6.23
     McKay
    3.78
     Kah
    3.73
     Malays
    3.60
     Cait
    3.40
     Jay
    3.33
     Kel
    3.22
    Activations Density 0.005%

    No Known Activations