© 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. 17099
    Prev
    Next
    INDEX
    Explanations

    references to the Keystone XL pipeline and associated political discussions

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

    No Comments

    Head Attr Weights
    0:0.21
    1:0.07
    2:0.03
    3:0.05
    4:0.03
    5:0.02
    6:0.11
    7:0.19
    8:0.03
    9:0.04
    10:0.11
    11:0.05
    Negative Logits
     Acer
    -3.36
     Firefly
    -3.27
     Gundam
    -3.13
     Cortex
    -3.04
     Stanton
    -2.98
     Robot
    -2.96
     Nero
    -2.85
     Marshal
    -2.76
     Saras
    -2.75
     joystick
    -2.75
    POSITIVE LOGITS
     Keystone
    5.12
     pipelines
    3.41
     Pipeline
    3.31
     pipeline
    3.29
    Oil
    3.28
     oil
    3.24
     fossil
    3.17
    oil
    3.09
     XL
    3.02
     Oil
    2.94
    Activations Density 0.008%

    No Known Activations