© 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. 23168
    Prev
    Next
    INDEX
    Explanations

    phrases related to human rights violations and criticisms of governmental actions

    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
    0:0.14
    1:0.08
    2:0.06
    3:0.06
    4:0.09
    5:0.02
    6:0.13
    7:0.18
    8:0.02
    9:0.04
    10:0.08
    11:0.06
    Negative Logits
     mathemat
    -2.79
    Scot
    -2.68
     chem
    -2.60
     Fiber
    -2.53
     neutron
    -2.44
     homebrew
    -2.40
     bowling
    -2.40
     Lyme
    -2.39
     sage
    -2.36
     gol
    -2.35
    POSITIVE LOGITS
     Amnesty
    4.42
     HRC
    4.04
    nesty
    3.72
     UNHCR
    3.54
     NGO
    3.52
     Human
    3.31
     Azerbai
    3.27
     Hague
    3.27
     Beirut
    3.26
     Palestine
    3.16
    Activations Density 0.077%

    No Known Activations