© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 22917
    Prev
    Next
    INDEX
    Explanations

    sentences discussing human rights issues, particularly related to Amnesty International's positions and reports

    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
    0:0.13
    1:0.08
    2:0.06
    3:0.06
    4:0.05
    5:0.03
    6:0.15
    7:0.16
    8:0.02
    9:0.05
    10:0.13
    11:0.04
    Negative Logits
    andom
    -2.75
     nerd
    -2.73
     pant
    -2.62
     Whitman
    -2.54
    Sty
    -2.52
     Wick
    -2.52
    Bear
    -2.47
     geek
    -2.37
    anke
    -2.36
    Thompson
    -2.36
    POSITIVE LOGITS
     Amnesty
    6.23
    nesty
    4.94
     UAE
    3.32
     Asylum
    3.30
     Kuwait
    3.28
     detainee
    3.27
    raq
    3.19
     UNHCR
    3.08
     Hamas
    3.03
     Bangl
    3.00
    Activations Density 0.005%

    No Known Activations