© 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. 10648
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "building" in various contexts

    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
    0:0.04
    1:0.02
    2:0.02
    3:0.03
    4:0.06
    5:0.04
    6:0.04
    7:0.07
    8:0.01
    9:0.10
    10:0.02
    11:0.50
    Negative Logits
     omission
    -2.21
     directions
    -2.19
    Director
    -2.18
     overheard
    -2.09
     Editors
    -2.08
     excerpt
    -2.01
    uties
    -1.98
    tesy
    -1.97
     direction
    -1.96
     Supervisor
    -1.95
    POSITIVE LOGITS
     fences
    3.68
     bridges
    3.62
     walls
    3.60
     structures
    3.58
     infrastructure
    3.22
     barriers
    3.03
     buildings
    2.96
     wall
    2.91
     fence
    2.89
     Walls
    2.87
    Activations Density 0.140%

    No Known Activations