© 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. 6671
    Prev
    Next
    INDEX
    Explanations

    expressions related to offers, proposals, or suggestions in conversations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.03
    2:0.08
    3:0.05
    4:0.06
    5:0.04
    6:0.25
    7:0.03
    8:0.06
    9:0.18
    10:0.02
    11:0.04
    Negative Logits
    stocks
    -3.95
    locks
    -3.84
    ikk
    -3.81
    Oak
    -3.73
     Oakland
    -3.59
     Tycoon
    -3.51
     Dai
    -3.50
    ells
    -3.46
    uti
    -3.42
    rek
    -3.36
    POSITIVE LOGITS
     Hem
    9.58
     Corm
    8.26
     hem
    5.94
     Worm
    5.03
     Herman
    4.36
     Hart
    4.05
    Hart
    4.00
     Rib
    3.98
     Horn
    3.86
    hem
    3.85
    Activations Density 0.001%

    No Known Activations