© 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. 17430
    Prev
    Next
    INDEX
    Explanations

    references to governmental policies and regulations

    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
    0:0.04
    1:0.02
    2:0.03
    3:0.12
    4:0.06
    5:0.12
    6:0.07
    7:0.07
    8:0.16
    9:0.19
    10:0.03
    11:0.03
    Negative Logits
    ..........
    -2.77
    uits
    -2.28
     ;;
    -2.25
     Span
    -2.25
    ã
    -2.22
     ―
    -2.18
    ,,,,
    -2.17
     ---
    -2.17
     literally
    -2.15
    uously
    -2.14
    POSITIVE LOGITS
    Mr
    4.42
     Mr
    4.19
     he
    3.56
    Analysis
    3.54
     Nato
    3.38
    He
    3.21
     Ms
    3.11
    Mrs
    3.10
    Shape
    3.08
    Labour
    3.00
    Activations Density 0.086%

    No Known Activations