© 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. 10-ATT-KK
    11. 9941
    Prev
    Next
    INDEX
    Explanations

    occurrences of legal or medical transgressions involving prescription drugs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.16
    1:0.08
    2:0.07
    3:0.05
    4:0.07
    5:0.03
    6:0.08
    7:0.11
    8:0.04
    9:0.06
    10:0.10
    11:0.08
    Negative Logits
     Lanka
    -3.16
     Mages
    -3.13
     Mous
    -3.01
     Mush
    -2.97
     Shard
    -2.94
    rive
    -2.90
    龍契士
    -2.84
     Murdoch
    -2.82
    printf
    -2.79
     Vij
    -2.69
    POSITIVE LOGITS
     oxy
    6.87
     Oxy
    4.59
    toc
    3.67
    oxy
    3.54
     hormones
    3.54
    OX
    3.51
     hormone
    3.40
     morphine
    3.21
     analges
    3.20
     uter
    3.17
    Activations Density 0.003%

    No Known Activations