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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43219
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with the Jewish Sabbath, particularly related to appliances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.12
    3:0.06
    4:0.05
    5:0.03
    6:0.12
    7:0.07
    8:0.03
    9:0.04
    10:0.33
    11:0.05
    Negative Logits
     sued
    -1.82
     blur
    -1.68
    embed
    -1.67
     WATCHED
    -1.66
     sue
    -1.66
     ejected
    -1.65
     empath
    -1.59
     jumped
    -1.59
     unintentionally
    -1.58
     sensations
    -1.57
    POSITIVE LOGITS
    isites
    2.05
     agenda
    1.96
     Topics
    1.89
    onday
    1.81
     calendar
    1.79
     tomorrow
    1.78
     calendars
    1.76
     Topic
    1.76
     Prepar
    1.72
    uci
    1.72
    Activations Density 0.000%

    No Known Activations