© 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. 17469
    Prev
    Next
    INDEX
    Explanations

    references to social issues and concerns related to gun violence and its impacts

    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
    0:0.22
    1:0.06
    2:0.08
    3:0.05
    4:0.02
    5:0.02
    6:0.13
    7:0.14
    8:0.02
    9:0.03
    10:0.10
    11:0.05
    Negative Logits
    Ring
    -3.18
     Slovenia
    -3.15
     Sloven
    -3.09
     Ring
    -3.05
     Kum
    -3.01
     Taj
    -2.93
     NXT
    -2.86
     Cedar
    -2.83
     Derrick
    -2.82
     caching
    -2.82
    POSITIVE LOGITS
     Shepard
    8.59
    pard
    5.95
     Cerberus
    5.56
     Garr
    5.44
     Normandy
    4.85
     Andromeda
    4.55
     Reaper
    4.43
    romeda
    3.90
     Poe
    3.71
    berus
    3.51
    Activations Density 0.003%

    No Known Activations