© 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. 10-ATT-KK
    11. 10709
    Prev
    Next
    INDEX
    Explanations

    phrases associated with legal or judicial proceedings

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.06
    1:0.05
    2:0.06
    3:0.04
    4:0.03
    5:0.04
    6:0.05
    7:0.09
    8:0.03
    9:0.05
    10:0.42
    11:0.03
    Negative Logits
     tem
    -4.12
     Em
    -3.37
     em
    -3.26
     Tam
    -3.05
     XD
    -3.00
     Qu
    -2.95
    IDA
    -2.87
     seiz
    -2.86
     princ
    -2.84
     Template
    -2.84
    POSITIVE LOGITS
    B
    7.13
    BN
    6.41
    BP
    6.13
     Burgess
    5.93
    BB
    5.91
    BF
    5.73
    BD
    5.62
    b
    5.52
    Bs
    5.50
    BW
    5.38
    Activations Density 0.173%

    No Known Activations