© 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. 2-ATT-KK
    11. 15902
    Prev
    Next
    INDEX
    Explanations

    words related to societal issues and controversies

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.05
    1:0.04
    2:0.23
    3:0.06
    4:0.13
    5:0.07
    6:0.03
    7:0.03
    8:0.09
    9:0.13
    10:0.07
    11:0.03
    Negative Logits
    ーテ
    -1.48
    udo
    -1.32
    ーティ
    -1.30
    soDeliveryDate
    -1.29
    ICAN
    -1.26
    �士
    -1.24
    ロ
    -1.24
     sugg
    -1.22
     Cosponsors
    -1.21
    igne
    -1.20
    POSITIVE LOGITS
     wid
    1.39
     widow
    1.37
    fold
    1.16
    Fed
    1.13
    utsche
    1.12
    ificate
    1.06
     recl
    1.05
     resent
    1.03
    hirt
    1.03
    lde
    1.03
    Activations Density 0.001%

    No Known Activations