© 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. 9-ATT-KK
    11. 5628
    Prev
    Next
    INDEX
    Explanations

    references to media comments and reactions related to political situations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.08
    1:0.03
    2:0.09
    3:0.04
    4:0.05
    5:0.05
    6:0.17
    7:0.07
    8:0.11
    9:0.19
    10:0.03
    11:0.04
    Negative Logits
     mercury
    -3.80
     Albion
    -3.50
     sulph
    -3.45
    sterdam
    -3.42
     asbestos
    -3.39
     ants
    -3.34
     AU
    -3.30
     Austral
    -3.19
     euth
    -3.16
     butterfly
    -3.14
    POSITIVE LOGITS
     Priebus
    10.06
    Pri
    7.48
     RNC
    5.26
     Bannon
    5.03
     Spicer
    4.71
     Pai
    4.61
     Pri
    4.06
    pri
    4.01
     Rollins
    4.01
     Priest
    3.95
    Activations Density 0.002%

    No Known Activations