© 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. 14321
    Prev
    Next
    INDEX
    Explanations

    descriptions of personal relationships with a focus on love and loyalty

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to personal relationships and emotional connections

    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
    0:0.22
    1:0.06
    2:0.05
    3:0.03
    4:0.11
    5:0.14
    6:0.09
    7:0.04
    8:0.05
    9:0.03
    10:0.09
    11:0.03
    Negative Logits
    ashington
    -1.46
    idespread
    -1.43
    WAR
    -1.43
    atories
    -1.33
    ré
    -1.29
    anse
    -1.27
    Published
    -1.26
    WARD
    -1.24
    Requ
    -1.21
    Counter
    -1.21
    POSITIVE LOGITS
    ..."
    1.56
     proble
    1.55
     hemor
    1.54
    xual
    1.54
    )",
    1.52
     clown
    1.49
     nig
    1.48
     fools
    1.48
     daddy
    1.48
     tyr
    1.47
    Activations Density 0.157%

    No Known Activations