© 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. 21763
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of," particularly in conjunction with geographical locations or groups

    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
    1:0.02
    2:0.06
    3:0.06
    4:0.18
    5:0.03
    6:0.11
    7:0.24
    8:0.04
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
    覚醒
    -1.37
     candle
    -1.36
    ewitness
    -1.30
    iday
    -1.23
     thereafter
    -1.22
     nails
    -1.21
     pores
    -1.20
     accordingly
    -1.19
    ocytes
    -1.19
    mination
    -1.16
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    1.41
     latitude
    1.26
     commodities
    1.23
    argon
    1.19
    ometown
    1.16
    idable
    1.16
    Land
    1.14
    ELD
    1.14
    qq
    1.14
     Anarchy
    1.12
    Activations Density 0.001%

    No Known Activations