© 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. 23301
    Prev
    Next
    INDEX
    Explanations

    references to infrastructure and construction projects

    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
    1:0.03
    2:0.03
    3:0.05
    4:0.06
    5:0.20
    6:0.03
    7:0.08
    8:0.03
    9:0.32
    10:0.03
    11:0.05
    Negative Logits
     ours
    -2.65
     vou
    -2.25
     categor
    -2.16
     stereotype
    -2.15
     hers
    -2.12
    heter
    -2.10
     plurality
    -2.03
     disapprove
    -2.02
     disappro
    -2.02
     Administ
    -2.00
    POSITIVE LOGITS
     begins
    2.75
     starts
    2.55
     Sands
    2.40
    ital
    2.30
     ramps
    2.27
     trenches
    2.26
     kicks
    2.24
     resumed
    2.22
     roots
    2.22
     rocks
    2.16
    Activations Density 0.014%

    No Known Activations