© 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. 6520
    Prev
    Next
    INDEX
    Explanations

    references to historical landmarks and monuments

    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
    0:0.10
    1:0.03
    2:0.02
    3:0.06
    4:0.07
    5:0.03
    6:0.05
    7:0.07
    8:0.02
    9:0.08
    10:0.03
    11:0.38
    Negative Logits
     testers
    -2.87
     Programming
    -2.65
     programmers
    -2.46
    drivers
    -2.42
     freel
    -2.37
     inexperienced
    -2.36
    ducers
    -2.35
    driver
    -2.26
     inexper
    -2.25
    Ops
    -2.22
    POSITIVE LOGITS
     monuments
    5.51
     monument
    5.25
     statues
    5.18
     statue
    4.96
     shrine
    4.68
     memorial
    4.49
     Statue
    4.25
     sculpture
    4.10
     sculptures
    4.03
     tomb
    3.95
    Activations Density 0.518%

    No Known Activations