Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 14019
    Prev
    Next
    INDEX
    Explanations

    mention of babies, births, medical procedures, and medical conditions related to children

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.06
    2:0.15
    3:0.06
    4:0.03
    5:0.10
    6:0.03
    7:0.04
    8:0.04
    9:0.28
    10:0.07
    11:0.03
    Negative Logits
    pmwiki
    -1.75
    isSpecialOrderable
    -1.61
    ーティ
    -1.42
    soDeliveryDate
    -1.39
     precedent
    -1.34
    entious
    -1.32
    iliate
    -1.31
     awarding
    -1.31
    機
    -1.31
     Ranking
    -1.29
    POSITIVE LOGITS
     nurse
    1.65
     captivity
    1.64
     syndrome
    1.62
     womb
    1.56
     careg
    1.50
     nurses
    1.50
    wings
    1.48
     kittens
    1.48
     Syndrome
    1.47
     ana
    1.43
    Activations Density 0.041%

    No Known Activations