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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 55
    Prev
    Next
    INDEX
    Explanations

    references to national holidays and celebrations, specifically focusing on Independence Day activities and traditions in the United States

    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
    0:0.13
    1:0.01
    2:0.32
    3:0.12
    4:0.04
    5:0.11
    6:0.03
    7:0.04
    8:0.05
    9:0.03
    10:0.04
    11:0.02
    Negative Logits
    ilage
    -2.51
    asive
    -2.38
     deposition
    -2.31
     biome
    -2.22
    eneg
    -2.22
     prote
    -2.22
     corrosion
    -2.21
    hesive
    -2.20
     impedance
    -2.17
    wark
    -2.17
    POSITIVE LOGITS
     holiday
    5.53
    holiday
    5.30
     festivities
    5.10
     celebration
    5.00
     holidays
    4.99
     celebrations
    4.88
     celebrating
    4.80
     Celebr
    4.74
     festive
    4.70
     Holiday
    4.65
    Activations Density 0.896%

    No Known Activations