© 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. 9-ATT-KK
    11. 15511
    Prev
    Next
    INDEX
    Explanations

    references to referendums and voting processes

    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
    0:0.06
    1:0.01
    2:0.12
    3:0.15
    4:0.03
    5:0.34
    6:0.02
    7:0.06
    8:0.06
    9:0.01
    10:0.06
    11:0.02
    Negative Logits
     crowds
    -2.73
     crowd
    -2.31
     attendees
    -2.28
     timed
    -2.23
    essen
    -2.18
     Participant
    -2.17
    ingers
    -2.14
    ossip
    -2.13
    ickets
    -2.13
     organizers
    -2.12
    POSITIVE LOGITS
     envis
    2.55
     Archangel
    2.17
    ilk
    2.07
     Anat
    2.03
    tymology
    2.02
     Exploration
    1.99
    isation
    1.95
    isations
    1.91
     Extend
    1.89
    utics
    1.89
    Activations Density 0.475%

    No Known Activations