© 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. 6947
    Prev
    Next
    INDEX
    Explanations

    statements and claims related to violence and its justification

    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
    0:0.12
    1:0.24
    2:0.03
    3:0.04
    4:0.03
    5:0.02
    6:0.06
    7:0.10
    8:0.02
    9:0.03
    10:0.23
    11:0.04
    Negative Logits
    ��
    -3.10
     Scorpion
    -2.96
    �
    -2.77
    irect
    -2.74
    inous
    -2.66
    Rich
    -2.60
    Gil
    -2.58
    ukong
    -2.51
    エル
    -2.48
    SourceFile
    -2.48
    POSITIVE LOGITS
     Bre
    9.47
    Bre
    7.77
    bre
    5.74
     BRE
    5.42
     bre
    5.36
     Breed
    4.15
    BRE
    3.80
     Breaker
    3.75
     Bere
    3.54
     Fre
    3.50
    Activations Density 0.008%

    No Known Activations