© 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. 10609
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports trades and team dynamics

    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
    0:0.26
    1:0.05
    2:0.04
    3:0.08
    4:0.04
    5:0.02
    6:0.10
    7:0.10
    8:0.02
    9:0.07
    10:0.13
    11:0.04
    Negative Logits
     Django
    -3.78
     Dj
    -3.71
     Savannah
    -3.71
     Nile
    -3.61
     Pharaoh
    -3.40
     zinc
    -3.33
     Guinea
    -3.29
     Tunisia
    -3.25
     Imran
    -3.22
     ANC
    -3.19
    POSITIVE LOGITS
     Leafs
    9.03
     Maple
    6.13
     Leaf
    5.65
    Toronto
    5.43
     Toronto
    5.26
     Carly
    5.16
     Raptors
    4.26
     NHL
    4.21
     Brendan
    4.21
     Lowry
    4.16
    Activations Density 0.012%

    No Known Activations