© 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. 16524
    Prev
    Next
    INDEX
    Explanations

    terms related to health and safety advice

    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
    0:0.28
    1:0.03
    2:0.04
    3:0.05
    4:0.06
    5:0.01
    6:0.11
    7:0.19
    8:0.01
    9:0.04
    10:0.07
    11:0.05
    Negative Logits
     Yor
    -3.62
     violin
    -3.42
     Sussex
    -3.39
     Yosemite
    -3.21
     whisky
    -3.18
     Jazz
    -3.17
     Aviv
    -3.15
     Jewish
    -3.13
     Galile
    -3.10
     Archae
    -3.06
    POSITIVE LOGITS
    UFC
    6.04
     UFC
    5.82
     MMA
    5.80
     Rouse
    4.83
     fighters
    4.13
     cage
    3.91
     Silva
    3.84
    nen
    3.73
     McGregor
    3.72
     Dana
    3.57
    Activations Density 0.092%

    No Known Activations