© 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. 10-ATT-KK
    11. 9335
    Prev
    Next
    INDEX
    Explanations

    references to human rights violations and the Rohingya crisis

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.18
    1:0.04
    2:0.05
    3:0.04
    4:0.04
    5:0.03
    6:0.06
    7:0.23
    8:0.02
    9:0.05
    10:0.15
    11:0.06
    Negative Logits
     Bowie
    -3.27
     MDMA
    -3.15
     Mellon
    -3.02
     Laurel
    -2.99
    acho
    -2.74
     morphine
    -2.72
     Vinyl
    -2.59
     Gaia
    -2.59
     Narc
    -2.56
     Cheryl
    -2.54
    POSITIVE LOGITS
     Rohing
    3.51
     Rohingya
    3.38
    Ro
    3.10
     Buddh
    2.78
     forc
    2.75
     Rath
    2.60
     persecution
    2.59
     Religious
    2.48
     Vive
    2.46
     persecuted
    2.44
    Activations Density 0.008%

    No Known Activations