© 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. 5331
    Prev
    Next
    INDEX
    Explanations

    nouns and terms associated with individuals and groups in various contexts, particularly related to regulations and societal roles

    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
    0:0.03
    1:0.05
    2:0.08
    3:0.04
    4:0.03
    5:0.05
    6:0.06
    7:0.06
    8:0.34
    9:0.05
    10:0.07
    11:0.09
    Negative Logits
     laughing
    -1.21
    ilogy
    -1.19
     Leviathan
    -1.15
     Doomsday
    -1.14
     Collider
    -1.13
     communism
    -1.13
    naire
    -1.09
     evils
    -1.09
     Dill
    -1.08
     Extras
    -1.07
    POSITIVE LOGITS
    omever
    1.36
    orers
    1.28
     counseling
    1.25
    ancers
    1.22
    isting
    1.20
    uri
    1.19
    ikan
    1.19
    uku
    1.17
    kw
    1.15
    emis
    1.15
    Activations Density 0.038%

    No Known Activations