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. 18759
    Prev
    Next
    INDEX
    Explanations

    references to political events and gatherings

    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
    0:0.10
    1:0.02
    2:0.15
    3:0.24
    4:0.05
    5:0.12
    6:0.02
    7:0.11
    8:0.03
    9:0.01
    10:0.08
    11:0.02
    Negative Logits
    agate
    -2.50
    conom
    -2.46
    cancer
    -2.32
    netflix
    -2.26
    utical
    -2.24
    directory
    -2.21
    profit
    -2.14
     dependency
    -2.11
    Downloadha
    -2.05
     Currently
    -2.05
    POSITIVE LOGITS
     applause
    4.13
     spectators
    3.88
     cheering
    3.85
     cheers
    3.75
     attendees
    3.58
     onlook
    3.56
     announcer
    3.33
     cheered
    3.27
     chanting
    3.26
     chants
    3.23
    Activations Density 1.332%

    No Known Activations