© 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. 17125
    Prev
    Next
    INDEX
    Explanations

    issues related to the effectiveness and integrity of institutions

    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
    0:0.08
    1:0.09
    2:0.06
    3:0.06
    4:0.06
    5:0.02
    6:0.18
    7:0.17
    8:0.02
    9:0.04
    10:0.06
    11:0.12
    Negative Logits
     Buster
    -2.17
    ーン
    -2.11
    パ
    -2.02
     Sold
    -1.99
    XY
    -1.99
    etchup
    -1.97
    plate
    -1.97
    translation
    -1.96
     Sprite
    -1.96
     palette
    -1.95
    POSITIVE LOGITS
     institutions
    4.63
     Instit
    4.34
     institution
    3.89
     institutional
    3.70
     instit
    3.14
     universities
    3.00
     trustees
    2.97
     Colleges
    2.94
     Universities
    2.90
     faculty
    2.87
    Activations Density 0.008%

    No Known Activations