© 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. 22896
    Prev
    Next
    INDEX
    Explanations

    references to industries, particularly those involving unethical practices or issues surrounding corruption and regulation

    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
    1:0.04
    2:0.04
    3:0.03
    4:0.05
    5:0.02
    6:0.20
    7:0.22
    8:0.02
    9:0.04
    10:0.03
    11:0.14
    Negative Logits
     Ramos
    -2.41
    card
    -2.05
     Oro
    -2.03
    obin
    -2.01
     Middles
    -1.99
    orable
    -1.94
     Zimmerman
    -1.93
    etsk
    -1.91
     roomm
    -1.90
     Mum
    -1.89
    POSITIVE LOGITS
    indust
    4.68
     industry
    4.38
     industries
    3.99
    Indust
    3.84
     Industry
    3.75
     trades
    2.95
    Companies
    2.89
     manufact
    2.89
     manufactures
    2.87
     sector
    2.85
    Activations Density 0.066%

    No Known Activations