© 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. 6775
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities, particularly in contexts like negotiations, agreements, or controversies

    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
    0:0.15
    1:0.15
    2:0.04
    3:0.07
    4:0.02
    5:0.01
    6:0.09
    7:0.12
    8:0.06
    9:0.02
    10:0.15
    11:0.07
    Negative Logits
     TN
    -2.61
     Charleston
    -2.58
     sher
    -2.58
     inhal
    -2.56
     Chero
    -2.54
     kay
    -2.53
     Yellowstone
    -2.51
     mamm
    -2.50
    ewski
    -2.49
     BCC
    -2.46
    POSITIVE LOGITS
     F
    3.85
    gerald
    3.81
     Fior
    3.50
     Feather
    3.44
     Ferrari
    3.43
     Fitzgerald
    3.40
     Ferr
    3.40
     Fen
    3.38
     Fe
    3.35
    ettel
    3.33
    Activations Density 0.009%

    No Known Activations