© 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. 3-ATT-KK
    11. 10793
    Prev
    Next
    INDEX
    Explanations

    phrases related to obligation and necessity in contexts of governance and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.05
    2:0.06
    3:0.02
    4:0.01
    5:0.04
    6:0.05
    7:0.05
    8:0.08
    9:0.38
    10:0.07
    11:0.12
    Negative Logits
    ェ
    -1.52
    jan
    -1.31
    mill
    -1.27
    lance
    -1.27
    MpServer
    -1.25
    terday
    -1.14
    cember
    -1.12
    arij
    -1.09
    Lind
    -1.08
    quickShipAvailable
    -1.08
    POSITIVE LOGITS
     reconsider
    1.30
    rifice
    1.28
     reproduce
    1.24
     consent
    1.20
     obey
    1.15
     unlaw
    1.14
    Commission
    1.14
     exempt
    1.13
     recomm
    1.13
     resusc
    1.12
    Activations Density 0.016%

    No Known Activations