© 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. 2-ATT-KK
    11. 11516
    Prev
    Next
    INDEX
    Explanations

    phrases with derogatory language or insults

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.14
    3:0.05
    4:0.05
    5:0.08
    6:0.04
    7:0.04
    8:0.06
    9:0.25
    10:0.07
    11:0.03
    Negative Logits
    ETF
    -1.70
    theless
    -1.51
    enhagen
    -1.50
    ortium
    -1.48
    catentry
    -1.44
    intendent
    -1.42
    isSpecialOrderable
    -1.37
    anwhile
    -1.33
    erness
    -1.33
    soDeliveryDate
    -1.33
    POSITIVE LOGITS
     bitch
    1.78
    shit
    1.69
     sucking
    1.61
     hates
    1.57
     Clown
    1.56
     shit
    1.55
     jerk
    1.53
     asshole
    1.53
     Creep
    1.50
    oops
    1.48
    Activations Density 0.023%

    No Known Activations