© 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. 9-ATT-KK
    11. 24062
    Prev
    Next
    INDEX
    Explanations

    phrases related to password security and management

    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
    0:0.22
    1:0.03
    2:0.23
    3:0.08
    4:0.03
    5:0.10
    6:0.04
    7:0.04
    8:0.06
    9:0.06
    10:0.03
    11:0.03
    Negative Logits
     Dayton
    -2.65
    Render
    -2.62
     rapt
    -2.60
     Towns
    -2.59
    odynamic
    -2.57
     displacement
    -2.44
     Galile
    -2.40
     Robertson
    -2.40
    ascular
    -2.35
     Engel
    -2.35
    POSITIVE LOGITS
     passwords
    6.95
     password
    6.66
    password
    6.51
    Password
    6.36
     Password
    5.88
     username
    4.57
     login
    4.35
     Username
    4.07
    username
    3.96
     hashes
    3.91
    Activations Density 0.047%

    No Known Activations