© 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. 23299
    Prev
    Next
    INDEX
    Explanations

    assertions related to tolerance and fairness

    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
    0:0.13
    1:0.10
    2:0.03
    3:0.04
    4:0.13
    5:0.02
    6:0.07
    7:0.20
    8:0.02
    9:0.05
    10:0.06
    11:0.09
    Negative Logits
    MET
    -2.52
     Mant
    -2.49
     Cabrera
    -2.47
    Medic
    -2.35
    ancial
    -2.30
     »
    -2.26
     Titan
    -2.25
    mares
    -2.24
     underwater
    -2.24
    »
    -2.22
    POSITIVE LOGITS
     tolerance
    4.32
    olerance
    4.19
     tolerant
    3.77
     intolerance
    3.77
    Jews
    3.46
     toler
    3.23
     intoler
    3.20
     Jews
    3.07
     bigot
    2.98
     bigotry
    2.98
    Activations Density 0.003%

    No Known Activations