© 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. 9653
    Prev
    Next
    INDEX
    Explanations

    references to government procurement and its associated issues, including corruption and unethical practices

    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
    0:0.10
    1:0.05
    2:0.06
    3:0.08
    4:0.07
    5:0.04
    6:0.19
    7:0.12
    8:0.05
    9:0.05
    10:0.07
    11:0.07
    Negative Logits
     largeDownload
    -3.31
     emanc
    -2.89
     "$:/
    -2.81
     exorc
    -2.71
     nig
    -2.52
     Observatory
    -2.49
    redits
    -2.42
     WWE
    -2.39
     ├
    -2.35
    casts
    -2.24
    POSITIVE LOGITS
     procurement
    4.82
     bidding
    3.62
     contracting
    3.04
     vendor
    2.88
     manufact
    2.87
     subcontract
    2.75
     eBay
    2.73
     bribery
    2.71
     procure
    2.68
     contractor
    2.65
    Activations Density 0.002%

    No Known Activations