© 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. 5559
    Prev
    Next
    INDEX
    Explanations

    a range of topics related to health and societal issues

    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
    0:0.03
    1:0.04
    2:0.16
    3:0.04
    4:0.02
    5:0.03
    6:0.09
    7:0.10
    8:0.12
    9:0.04
    10:0.04
    11:0.21
    Negative Logits
     Proud
    -1.50
     Democracy
    -1.48
     Shutterstock
    -1.46
     Pastebin
    -1.38
     Tik
    -1.23
     teaser
    -1.21
     Wife
    -1.20
     Democr
    -1.20
     Sovere
    -1.20
     Kappa
    -1.19
    POSITIVE LOGITS
     descript
    1.65
    levels
    1.59
     imaginable
    1.51
     equivalents
    1.42
    depending
    1.40
    ibilities
    1.39
    agents
    1.38
    姫
    1.38
     goodies
    1.37
     increments
    1.36
    Activations Density 0.011%

    No Known Activations