© 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. 5-ATT-KK
    11. 24739
    Prev
    Next
    INDEX
    Explanations

    references to boycotts and their implications

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.07
    3:0.05
    4:0.05
    5:0.03
    6:0.13
    7:0.07
    8:0.04
    9:0.04
    10:0.30
    11:0.12
    Negative Logits
     Guid
    -1.59
     Gry
    -1.54
     Piano
    -1.51
    ourses
    -1.48
     VIDE
    -1.42
     Instructor
    -1.42
    RH
    -1.41
     Arche
    -1.41
    eteria
    -1.39
    QUI
    -1.37
    POSITIVE LOGITS
     boycot
    1.98
     boycott
    1.97
     divest
    1.84
     destro
    1.60
     effected
    1.51
     cessation
    1.51
    consumer
    1.46
    entity
    1.45
     solidarity
    1.36
     bandwagon
    1.36
    Activations Density 0.001%

    No Known Activations