© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 5433
    Prev
    Next
    INDEX
    Explanations

    references to significant news events or incidents involving violence or political actions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.02
    1:0.23
    2:0.06
    3:0.03
    4:0.03
    5:0.03
    6:0.10
    7:0.09
    8:0.17
    9:0.04
    10:0.09
    11:0.05
    Negative Logits
    !),
    -1.29
    }.
    -1.25
    ),"
    -1.25
    ),
    -1.21
    ,)
    -1.18
    bsite
    -1.15
    ).
    -1.10
    !).
    -1.10
     persuasion
    -1.09
    )...
    -1.09
    POSITIVE LOGITS
    oglu
    1.49
    joice
    1.46
    DragonMagazine
    1.42
    odcast
    1.37
    ichever
    1.30
    isoft
    1.29
    ourning
    1.29
    BuyableInstoreAndOnline
    1.29
    theless
    1.24
     guiName
    1.23
    Activations Density 0.031%

    No Known Activations