© 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. 6650
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express personal opinions or sentiments

    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
    0:0.16
    1:0.06
    2:0.09
    3:0.06
    4:0.04
    5:0.03
    6:0.16
    7:0.14
    8:0.02
    9:0.03
    10:0.13
    11:0.04
    Negative Logits
     Sharks
    -3.36
    Pak
    -3.08
     Zan
    -2.88
     Chern
    -2.85
     redes
    -2.73
     Sochi
    -2.73
     Lua
    -2.70
     DV
    -2.68
    Wan
    -2.66
    obyl
    -2.65
    POSITIVE LOGITS
     Jefferson
    7.76
     Lafayette
    4.35
    Jeff
    3.92
     Randolph
    3.85
     Madison
    3.82
     Monroe
    3.65
     Adams
    3.54
    Madison
    3.40
     Jackson
    3.33
     Truman
    3.29
    Activations Density 0.010%

    No Known Activations