© 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. 2069
    Prev
    Next
    INDEX
    Explanations

    references to passwords and account security

    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
    0:0.05
    1:0.05
    2:0.07
    3:0.06
    4:0.06
    5:0.05
    6:0.19
    7:0.04
    8:0.04
    9:0.26
    10:0.05
    11:0.04
    Negative Logits
     Dispatch
    -4.10
     Robertson
    -4.04
     Rowe
    -3.17
    Dispatch
    -3.14
    frame
    -3.14
     Dayton
    -3.12
    frames
    -3.12
     Tanzania
    -3.07
    endas
    -3.01
    ahime
    -2.96
    POSITIVE LOGITS
     passwords
    6.23
     password
    6.05
    Password
    5.87
     Password
    5.64
    password
    5.30
    PASS
    4.78
     PASS
    4.33
     Kali
    3.59
     Azerbai
    3.44
     Pass
    3.40
    Activations Density 0.000%

    No Known Activations