© 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. 9823
    Prev
    Next
    INDEX
    Explanations

    references to coerced or forced actions related to bodily functions and legal implications

    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
    0:0.11
    1:0.02
    2:0.11
    3:0.06
    4:0.04
    5:0.07
    6:0.18
    7:0.05
    8:0.04
    9:0.21
    10:0.03
    11:0.03
    Negative Logits
     Chain
    -3.56
    Gear
    -3.38
     Grimoire
    -3.28
    �
    -3.08
    Forest
    -3.08
    Hor
    -3.08
     Windsor
    -3.08
    Cas
    -3.06
     Harmony
    -3.05
    atform
    -3.04
    POSITIVE LOGITS
     urine
    8.78
     pee
    7.50
     semen
    6.08
     ur
    5.97
     urinary
    5.82
     ejac
    5.77
     piss
    5.39
     bladder
    5.30
    pee
    4.40
     toilet
    4.35
    Activations Density 0.001%

    No Known Activations