© 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. 9-ATT-KK
    11. 5625
    Prev
    Next
    INDEX
    Explanations

    references to Alberta's energy sector and regulatory issues

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.05
    3:0.04
    4:0.03
    5:0.05
    6:0.07
    7:0.04
    8:0.48
    9:0.06
    10:0.02
    11:0.03
    Negative Logits
     Luigi
    -4.58
     Rhode
    -4.17
     Palest
    -4.12
     Sicily
    -3.98
     FDR
    -3.95
    umenthal
    -3.84
     Kaine
    -3.84
     Schumer
    -3.74
    lio
    -3.66
     Verizon
    -3.66
    POSITIVE LOGITS
     Alberta
    9.31
     Edmonton
    8.96
     Calgary
    8.75
     Saskatchewan
    7.14
    Albert
    6.78
    monton
    6.49
     Oilers
    6.26
     Manitoba
    6.26
     Leth
    6.23
     Sask
    6.20
    Activations Density 0.058%

    No Known Activations