© 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. 11980
    Prev
    Next
    INDEX
    Explanations

    information related to violent incidents and casualties

    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
    0:0.23
    1:0.11
    2:0.07
    3:0.06
    4:0.05
    5:0.03
    6:0.09
    7:0.09
    8:0.03
    9:0.05
    10:0.07
    11:0.06
    Negative Logits
     Lilly
    -3.34
     Nib
    -3.10
     yog
    -3.09
     IEEE
    -3.07
     Parm
    -3.03
     Hermes
    -3.01
     Yoga
    -3.00
     Camel
    -2.96
     Friedman
    -2.96
     Cele
    -2.94
    POSITIVE LOGITS
     Roof
    8.08
     Charleston
    4.71
     Confederate
    4.12
     Pastor
    3.71
     negro
    3.68
     pastor
    3.60
     Negro
    3.46
     hood
    3.42
     Hood
    3.41
     racially
    3.23
    Activations Density 0.000%

    No Known Activations