© 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. 10-ATT-KK
    11. 10880
    Prev
    Next
    INDEX
    Explanations

    references to relationships and interactions in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.10
    1:0.06
    2:0.08
    3:0.04
    4:0.04
    5:0.02
    6:0.17
    7:0.19
    8:0.02
    9:0.03
    10:0.07
    11:0.12
    Negative Logits
     Charity
    -2.46
     Channel
    -2.36
    Episode
    -2.35
     Episode
    -2.24
     Stream
    -2.22
    Season
    -2.19
     Katrina
    -2.19
     Comet
    -2.17
     Flood
    -2.11
     Film
    -2.10
    POSITIVE LOGITS
     desks
    4.33
     desk
    3.79
     chairs
    3.32
     chair
    3.07
     Desk
    2.76
     drawer
    2.68
    chairs
    2.56
    Desk
    2.55
     erg
    2.54
     workspace
    2.54
    Activations Density 0.001%

    No Known Activations