© 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. 19519
    Prev
    Next
    INDEX
    Explanations

    elements related to ethics and oversight in government or organizational contexts

    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
    0:0.10
    1:0.01
    2:0.30
    3:0.07
    4:0.03
    5:0.13
    6:0.06
    7:0.04
    8:0.07
    9:0.08
    10:0.03
    11:0.03
    Negative Logits
    Population
    -3.18
     Prediction
    -3.00
    igrants
    -2.99
    ュ
    -2.99
     bombers
    -2.97
    vik
    -2.81
    mingham
    -2.77
    population
    -2.74
     Population
    -2.73
     Bomber
    -2.72
    POSITIVE LOGITS
     ethics
    7.10
     Ethics
    6.34
     ethical
    5.66
     unethical
    4.82
    ethical
    4.37
     disclosure
    3.87
    Eth
    3.87
     disclosures
    3.63
     Eth
    3.60
     Integrity
    3.56
    Activations Density 0.018%

    No Known Activations