© 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. 2-ATT-KK
    11. 11478
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters such as court decisions, lawsuits, and legal obligations

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.10
    1:0.01
    2:0.17
    3:0.04
    4:0.07
    5:0.12
    6:0.04
    7:0.05
    8:0.15
    9:0.03
    10:0.10
    11:0.05
    Negative Logits
     Saga
    -1.03
     notebook
    -1.00
     Tracker
    -0.99
     surrounds
    -0.96
     Oz
    -0.96
     puzzle
    -0.94
     Outbreak
    -0.93
     Rub
    -0.93
     abyss
    -0.92
     labyrinth
    -0.92
    POSITIVE LOGITS
     suffice
    1.42
    icable
    1.41
    inarily
    1.20
     ASAP
    1.15
    FORM
    1.10
    Cho
    1.03
    erto
    1.03
    uate
    1.01
    angan
    1.00
    yg
    1.00
    Activations Density 0.119%

    No Known Activations