© 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. 23081
    Prev
    Next
    INDEX
    Explanations

    questions and remarks about public perceptions of political figures and events

    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
    0:0.15
    1:0.08
    2:0.08
    3:0.09
    4:0.04
    5:0.02
    6:0.18
    7:0.07
    8:0.03
    9:0.04
    10:0.11
    11:0.06
    Negative Logits
     detach
    -3.13
    atche
    -3.13
    Ult
    -3.04
    resy
    -2.93
     Sas
    -2.89
     Sorceress
    -2.86
     Ult
    -2.72
     Reincarnated
    -2.70
     Sau
    -2.69
    Sov
    -2.67
    POSITIVE LOGITS
    Bloomberg
    8.65
     Bloomberg
    8.40
     CNBC
    4.83
     JPMorgan
    4.42
     Giuliani
    4.14
     JPM
    4.11
     Gotham
    3.88
     Billion
    3.76
     bankers
    3.71
     Fortune
    3.58
    Activations Density 0.019%

    No Known Activations