© 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. 5355
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditional actions or relationships

    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
    0:0.01
    1:0.04
    2:0.06
    3:0.03
    4:0.02
    5:0.18
    6:0.06
    7:0.06
    8:0.09
    9:0.16
    10:0.08
    11:0.16
    Negative Logits
    ensor
    -1.58
     Fors
    -1.47
     Yorkshire
    -1.39
     Downing
    -1.36
    atile
    -1.33
    sold
    -1.31
    paid
    -1.29
     undisclosed
    -1.27
     CBI
    -1.25
     endorsements
    -1.25
    POSITIVE LOGITS
     proble
    1.83
    Solution
    1.72
    Problem
    1.57
     =================
    1.55
    EVA
    1.53
    asy
    1.53
    ambo
    1.52
    -|
    1.51
    ntax
    1.50
    acket
    1.45
    Activations Density 0.022%

    No Known Activations