© 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. 5453
    Prev
    Next
    INDEX
    Explanations

    patterns of repetition or emphasis in language

    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
    1:0.10
    2:0.17
    3:0.03
    4:0.01
    5:0.03
    6:0.09
    7:0.10
    8:0.15
    9:0.17
    10:0.04
    11:0.04
    Negative Logits
     Ended
    -1.22
     Gaul
    -1.14
     Lansing
    -1.14
    ���
    -1.13
     Edit
    -1.13
     wore
    -1.13
     LW
    -1.05
     Sark
    -1.05
     recovers
    -1.05
     }}
    -1.04
    POSITIVE LOGITS
    icky
    1.42
    erial
    1.40
    emonic
    1.34
    ceivable
    1.34
    nah
    1.33
     Beir
    1.28
     understatement
    1.28
    フォ
    1.24
    PLIED
    1.24
    aterasu
    1.24
    Activations Density 0.221%

    No Known Activations