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. 1-ATT-KK
    6. 6271
    Prev
    Next
    INDEX
    Explanations

    words related to childcare and babysitting

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.13
    1:0.05
    2:0.05
    3:0.03
    4:0.05
    5:0.07
    6:0.32
    7:0.06
    8:0.04
    9:0.04
    10:0.04
    11:0.07
    Negative Logits
     Peak
    -1.79
     fireball
    -1.72
    outube
    -1.67
    ��
    -1.63
     MSM
    -1.61
    urat
    -1.61
    SpaceEngineers
    -1.61
    ________________
    -1.60
    negie
    -1.60
    igslist
    -1.60
    POSITIVE LOGITS
     nursery
    2.27
     careg
    1.98
     babys
    1.95
     todd
    1.94
     nurs
    1.87
    washer
    1.85
    whel
    1.84
    manager
    1.84
     nursing
    1.83
     roles
    1.83
    Activations Density 0.001%

    No Known Activations