© 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. 9-ATT-KK
    11. 22877
    Prev
    Next
    INDEX
    Explanations

    phrases related to hacking and cybersecurity

    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
    0:0.08
    1:0.03
    2:0.12
    3:0.04
    4:0.06
    5:0.04
    6:0.18
    7:0.04
    8:0.06
    9:0.25
    10:0.03
    11:0.03
    Negative Logits
    perse
    -3.88
     Flavoring
    -3.58
    uer
    -3.48
    erva
    -3.48
     Pel
    -3.39
     mmol
    -3.32
    Parent
    -3.27
     Pall
    -3.26
    ynes
    -3.23
     Patel
    -3.09
    POSITIVE LOGITS
     Hack
    8.80
     hack
    8.67
    Hack
    8.47
     hackers
    8.45
     hacker
    8.39
     hacking
    8.07
     hacks
    8.06
    hack
    7.90
     Hacker
    7.79
     hacked
    7.30
    Activations Density 0.009%

    No Known Activations