© 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. 10-ATT-KK
    11. 12003
    Prev
    Next
    INDEX
    Explanations

    references to endangered species or ecological concerns

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.20
    1:0.07
    2:0.06
    3:0.08
    4:0.07
    5:0.04
    6:0.10
    7:0.05
    8:0.03
    9:0.05
    10:0.14
    11:0.04
    Negative Logits
     Cambod
    -4.64
     Romanian
    -4.39
     Cambodia
    -4.13
     Bulgar
    -3.87
     Rohingya
    -3.77
     bladder
    -3.65
    �
    -3.60
     Kub
    -3.56
     Rohing
    -3.56
    oğ
    -3.50
    POSITIVE LOGITS
     Devils
    8.54
     NJ
    5.06
    NJ
    4.99
     Devil
    4.92
     Newark
    4.28
     Elias
    4.28
     Christie
    4.26
    Dev
    4.07
    DN
    3.99
     NM
    3.92
    Activations Density 0.003%

    No Known Activations