© 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. 9-ATT-KK
    11. 5791
    Prev
    Next
    INDEX
    Explanations

    references to updates and new features in video games

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.13
    1:0.02
    2:0.07
    3:0.09
    4:0.04
    5:0.09
    6:0.08
    7:0.05
    8:0.26
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
     Caucasus
    -3.22
     lightsaber
    -3.16
    Thor
    -3.07
     Vader
    -2.89
     resh
    -2.75
     Sith
    -2.73
     Kling
    -2.65
     Bannon
    -2.62
     Asgard
    -2.59
    akh
    -2.58
    POSITIVE LOGITS
     Animal
    4.19
     Mushroom
    3.94
     Luigi
    3.90
    Animal
    3.77
     Clement
    3.39
     Chili
    3.39
     Toad
    3.39
     Balloon
    3.32
     Guatem
    3.27
     pineapple
    3.20
    Activations Density 0.003%

    No Known Activations