© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 15644
    Prev
    Next
    INDEX
    Explanations

    references to community engagement and inappropriate actions by companies or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.18
    1:0.02
    2:0.09
    3:0.08
    4:0.04
    5:0.05
    6:0.12
    7:0.03
    8:0.20
    9:0.10
    10:0.02
    11:0.02
    Negative Logits
     Yon
    -3.58
     Tok
    -3.29
     lantern
    -3.24
     mosqu
    -3.24
     Juda
    -3.23
     Shir
    -3.18
     Lev
    -3.15
     Aman
    -3.14
     Yose
    -3.13
    א
    -3.08
    POSITIVE LOGITS
     EA
    8.50
     Battlefield
    7.33
    EA
    7.10
     BF
    5.87
     Madden
    5.55
     FIFA
    5.14
     eSports
    4.66
    IFA
    4.57
     Hockey
    4.50
     Blizzard
    4.14
    Activations Density 0.006%

    No Known Activations