© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 19460
    Prev
    Next
    INDEX
    Explanations

    phrases related to overtime work and its regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.04
    2:0.19
    3:0.05
    4:0.06
    5:0.06
    6:0.12
    7:0.05
    8:0.08
    9:0.13
    10:0.03
    11:0.06
    Negative Logits
     Kamp
    -3.32
     embr
    -3.11
     Leeds
    -3.00
     Mb
    -2.98
    iasis
    -2.95
     Neph
    -2.94
     aph
    -2.90
     BCC
    -2.87
     enqu
    -2.81
     Mk
    -2.80
    POSITIVE LOGITS
     overtime
    7.32
     Overt
    5.24
     OT
    4.05
     EMS
    3.73
     shootout
    3.48
     anesthesia
    3.47
     paramedics
    3.45
     Tort
    3.39
     UPS
    3.35
     Otto
    3.34
    Activations Density 0.003%

    No Known Activations