© 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. 3-ATT-KK
    11. 5567
    Prev
    Next
    INDEX
    Explanations

    phrases related to invasive actions or harm

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.08
    2:0.12
    3:0.04
    4:0.01
    5:0.07
    6:0.07
    7:0.05
    8:0.07
    9:0.27
    10:0.09
    11:0.06
    Negative Logits
     ABE
    -1.15
    OUP
    -1.10
    imates
    -1.09
    oup
    -1.09
    mite
    -1.09
    mbuds
    -1.05
     ank
    -1.04
    $.
    -1.04
    AMA
    -1.03
    Extra
    -1.03
    POSITIVE LOGITS
    ··
    1.20
    matically
    1.12
    iris
    1.10
     Lieberman
    1.08
     meanwhile
    1.07
     Cassidy
    1.06
     Roche
    1.04
    stead
    1.02
    leaf
    1.00
    lying
    0.99
    Activations Density 0.155%

    No Known Activations