© 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. 9-ATT-KK
    11. 6362
    Prev
    Next
    INDEX
    Explanations

    mentions of violence and significant actions involving individuals

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.04
    1:0.07
    2:0.05
    3:0.11
    4:0.04
    5:0.09
    6:0.08
    7:0.05
    8:0.03
    9:0.12
    10:0.05
    11:0.22
    Negative Logits
     Buch
    -2.74
     Gamble
    -2.67
     Chambers
    -2.53
     Bubble
    -2.50
     Mahjong
    -2.48
     ('
    -2.43
     Grave
    -2.43
     Chess
    -2.43
     Mog
    -2.37
     Kinder
    -2.34
    POSITIVE LOGITS
    ctl
    3.22
    RN
    2.90
    cox
    2.88
    nance
    2.88
    iol
    2.85
    onz
    2.78
    phrine
    2.67
    alions
    2.66
    eq
    2.64
    %)
    2.63
    Activations Density 0.002%

    No Known Activations