© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 13592
    Prev
    Next
    INDEX
    Explanations

    discussions about privacy and security-related issues with data and information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.09
    2:0.11
    3:0.08
    4:0.03
    5:0.06
    6:0.03
    7:0.05
    8:0.05
    9:0.27
    10:0.09
    11:0.03
    Negative Logits
    illon
    -1.73
    undred
    -1.57
    addle
    -1.55
    ugi
    -1.53
    ench
    -1.51
    aughters
    -1.48
    姫
    -1.46
    ogie
    -1.45
    ixties
    -1.41
    aug
    -1.39
    POSITIVE LOGITS
     Privacy
    1.95
    Privacy
    1.86
     privacy
    1.69
     confidentiality
    1.64
     BlackBerry
    1.64
     VPN
    1.47
     Blockchain
    1.44
     CMS
    1.43
     confidential
    1.42
     arbitration
    1.41
    Activations Density 0.021%

    No Known Activations