© 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. 5368
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reserved" and variations of the word "secure."

    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
    0:0.47
    1:0.02
    2:0.04
    3:0.03
    4:0.06
    5:0.03
    6:0.06
    7:0.06
    8:0.04
    9:0.02
    10:0.08
    11:0.05
    Negative Logits
    NOW
    -1.64
     AGA
    -1.48
     Johann
    -1.47
    BuyableInstoreAndOnline
    -1.44
    doi
    -1.44
     Coch
    -1.38
     lacking
    -1.35
     faithfully
    -1.32
     Simulator
    -1.30
     Matth
    -1.28
    POSITIVE LOGITS
    ed
    1.80
    izers
    1.73
    est
    1.62
    ned
    1.58
    tan
    1.57
    izations
    1.54
    irection
    1.54
    cess
    1.52
    emed
    1.51
    ness
    1.50
    Activations Density 0.254%

    No Known Activations