© 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. 3-ATT-KK
    11. 14513
    Prev
    Next
    INDEX
    Explanations

    politically related words and mentions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to political figures and their affiliations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.11
    2:0.11
    3:0.05
    4:0.05
    5:0.07
    6:0.09
    7:0.10
    8:0.07
    9:0.06
    10:0.11
    11:0.08
    Negative Logits
     Heist
    -1.40
     hindsight
    -1.32
     antioxid
    -1.29
     Carib
    -1.27
     Kinnikuman
    -1.21
     Inquisition
    -1.20
    Reviewer
    -1.19
     Guides
    -1.17
     nowadays
    -1.17
     catalogue
    -1.16
    POSITIVE LOGITS
    ldon
    1.37
    rette
    1.36
    ospons
    1.34
    inguished
    1.31
    pel
    1.31
    iencies
    1.28
    anan
    1.27
    akis
    1.25
    chio
    1.23
    ibia
    1.23
    Activations Density 0.013%

    No Known Activations