© 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. 17459
    Prev
    Next
    INDEX
    Explanations

    references to ownership and decisions made by owners in a sports context

    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
    1:0.03
    2:0.04
    3:0.07
    4:0.05
    5:0.02
    6:0.14
    7:0.12
    8:0.02
    9:0.05
    10:0.10
    11:0.04
    Negative Logits
     Suffolk
    -3.78
     Sakuya
    -3.70
     Lowell
    -3.67
     Baltic
    -3.58
     Grimm
    -3.41
     Cuomo
    -3.36
     Maharashtra
    -3.34
    Yang
    -3.33
     Belarus
    -3.28
    Balt
    -3.22
    POSITIVE LOGITS
     Cowboys
    8.24
     Romo
    7.11
    Dallas
    5.58
    Cow
    5.46
     Dallas
    5.38
     Ezekiel
    5.30
     Cowboy
    4.78
     Dak
    4.56
     Prescott
    4.29
     Jerry
    4.06
    Activations Density 0.024%

    No Known Activations