© 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. 3-ATT-KK
    11. 5485
    Prev
    Next
    INDEX
    Explanations

    references to polling or survey data regarding public opinion, particularly involving Quinnipiac University

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.06
    2:0.07
    3:0.17
    4:0.03
    5:0.03
    6:0.16
    7:0.09
    8:0.04
    9:0.08
    10:0.06
    11:0.11
    Negative Logits
    TYPE
    -1.08
     fertilizer
    -0.99
     jew
    -0.98
     Zoro
    -0.97
    FIELD
    -0.97
     symbols
    -0.96
     worsh
    -0.96
     indoctr
    -0.94
     medicines
    -0.94
     cloves
    -0.94
    POSITIVE LOGITS
    ilver
    1.35
    gate
    1.28
    unia
    1.14
    rette
    1.07
    atl
    1.07
     Eag
    1.07
    itis
    1.07
    imester
    1.06
    iasco
    1.04
    amic
    1.04
    Activations Density 0.002%

    No Known Activations