© 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. 5559
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to decision-making and future intentions

    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
    0:0.07
    1:0.14
    2:0.11
    3:0.05
    4:0.03
    5:0.04
    6:0.13
    7:0.03
    8:0.03
    9:0.27
    10:0.03
    11:0.02
    Negative Logits
     Booker
    -4.08
     Berger
    -3.67
    artz
    -3.61
     Zap
    -3.59
     Trib
    -3.58
     Calder
    -3.58
    Buff
    -3.56
     Chou
    -3.51
     Colossus
    -3.37
     Rage
    -3.25
    POSITIVE LOGITS
    keep
    5.62
     stay
    4.79
     stays
    4.69
    keeping
    4.57
     maintenance
    4.54
     keep
    4.46
     maintain
    4.40
    Keep
    4.33
     keeping
    4.26
    Keeping
    4.22
    Activations Density 0.015%

    No Known Activations