© 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. 9-ATT-KK
    11. 5435
    Prev
    Next
    INDEX
    Explanations

    mentions of ethnic relations and tensions in societal contexts

    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
    0:0.09
    1:0.03
    2:0.07
    3:0.04
    4:0.07
    5:0.06
    6:0.18
    7:0.07
    8:0.10
    9:0.18
    10:0.02
    11:0.04
    Negative Logits
    Atl
    -4.19
     Carnival
    -3.52
    ajor
    -3.42
    indal
    -3.27
     Atlantis
    -3.26
     prom
    -3.25
    esm
    -3.25
     Atl
    -3.11
    monster
    -3.07
     Hob
    -3.07
    POSITIVE LOGITS
     Wei
    7.88
     Zhang
    7.70
     Xu
    6.30
     Zhou
    5.96
     Zhao
    5.81
     Wu
    5.72
     Cheng
    5.49
     Wang
    5.49
     Zhu
    5.25
     Yuan
    5.03
    Activations Density 0.010%

    No Known Activations