© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 21637
    Prev
    Next
    INDEX
    Explanations

    phrases related to obligatory or mandatory conditions and regulations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.13
    3:0.07
    4:0.16
    5:0.02
    6:0.04
    7:0.25
    8:0.03
    9:0.03
    10:0.11
    11:0.07
    Negative Logits
    apor
    -1.86
    vantage
    -1.72
    ilibrium
    -1.67
    imity
    -1.58
    avorable
    -1.52
    ellect
    -1.50
    augh
    -1.50
    igrated
    -1.44
    ression
    -1.43
    arton
    -1.42
    POSITIVE LOGITS
     Schedule
    1.75
     curfew
    1.72
     mandatory
    1.61
     compulsory
    1.53
     swearing
    1.53
    soDeliveryDate
    1.51
     oath
    1.50
     solemn
    1.44
     volunt
    1.43
     fortnight
    1.42
    Activations Density 0.001%

    No Known Activations