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

    Neuronpedia

    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. 5-ATT-KK
    11. 19079
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to safety and security in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.10
    3:0.05
    4:0.11
    5:0.02
    6:0.04
    7:0.39
    8:0.03
    9:0.04
    10:0.08
    11:0.06
    Negative Logits
    issance
    -1.82
    acio
    -1.81
    cart
    -1.67
     obsessed
    -1.57
     nostalg
    -1.56
    orig
    -1.54
     Yamato
    -1.47
    ventures
    -1.45
    ERN
    -1.39
     obsession
    -1.39
    POSITIVE LOGITS
     safest
    1.74
     safe
    1.72
     unprotected
    1.70
     secure
    1.68
     Secure
    1.63
     bunker
    1.59
     snakes
    1.54
     safer
    1.54
     risk
    1.52
     Safe
    1.52
    Activations Density 0.025%

    No Known Activations