© 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. 22035
    Prev
    Next
    INDEX
    Explanations

    references to war-related imagery and events

    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
    0:0.11
    1:0.04
    2:0.04
    3:0.05
    4:0.08
    5:0.02
    6:0.32
    7:0.09
    8:0.02
    9:0.05
    10:0.06
    11:0.08
    Negative Logits
    Train
    -3.04
     isolate
    -3.03
    train
    -2.91
     train
    -2.88
    orthern
    -2.79
     isol
    -2.75
    resso
    -2.74
    coord
    -2.66
     expel
    -2.57
    renheit
    -2.54
    POSITIVE LOGITS
     auction
    9.22
     auctions
    8.87
     Auction
    8.10
     bidder
    7.76
     bidding
    7.60
     bids
    6.49
    uctions
    6.38
     eBay
    6.00
     buyer
    5.94
     buyers
    5.88
    Activations Density 0.091%

    No Known Activations