© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10309
    Prev
    Next
    INDEX
    Explanations

    references to violence and oppression, particularly related to human rights abuses

    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
    0:0.10
    1:0.01
    2:0.36
    3:0.12
    4:0.03
    5:0.09
    6:0.04
    7:0.05
    8:0.08
    9:0.01
    10:0.04
    11:0.02
    Negative Logits
     Pebble
    -2.90
    Premium
    -2.85
     bounce
    -2.62
    nergy
    -2.62
    nect
    -2.59
    duino
    -2.57
    Hamilton
    -2.56
    ynthesis
    -2.50
    iquid
    -2.47
     CNBC
    -2.46
    POSITIVE LOGITS
     massacres
    6.04
     killings
    5.79
     genocide
    5.75
     atrocities
    5.75
     atroc
    5.66
     massacre
    5.63
     slaughter
    5.59
     murderers
    5.59
     murders
    5.49
     executions
    5.42
    Activations Density 1.112%

    No Known Activations