© 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. 9-ATT-KK
    11. 318
    Prev
    Next
    INDEX
    Explanations

    terms related to illegal substances and related legal issues

    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
    2:0.11
    3:0.21
    4:0.04
    5:0.16
    6:0.03
    7:0.06
    8:0.04
    9:0.03
    10:0.15
    11:0.02
    Negative Logits
     winters
    -2.10
    aterasu
    -2.02
     retire
    -1.85
    iscover
    -1.77
     exodus
    -1.73
     careers
    -1.73
     Zar
    -1.72
     summers
    -1.71
     lawy
    -1.68
     retirement
    -1.66
    POSITIVE LOGITS
    amphetamine
    2.16
    stasy
    2.14
     methamphetamine
    2.12
     Substance
    2.03
     (£
    1.96
     resin
    1.93
     quantities
    1.90
     possessed
    1.89
     cocaine
    1.88
     oxy
    1.82
    Activations Density 0.024%

    No Known Activations