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. 3130
    Prev
    Next
    INDEX
    Explanations

    topics related to historical governance, societal structures, and cultural influences

    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
    0:0.04
    1:0.02
    2:0.06
    3:0.18
    4:0.03
    5:0.11
    6:0.02
    7:0.09
    8:0.04
    9:0.01
    10:0.32
    11:0.02
    Negative Logits
     deadline
    -2.14
    ullivan
    -2.12
    �醒
    -2.02
    HQ
    -1.90
    Loading
    -1.89
     isEnabled
    -1.85
    widget
    -1.81
     expects
    -1.75
    Tyler
    -1.75
     bidder
    -1.73
    POSITIVE LOGITS
     centuries
    3.66
     millennia
    3.53
     ancestors
    3.26
     prior
    3.18
     antiquity
    3.17
     ancestor
    3.04
     decades
    2.87
     preceding
    2.79
     ago
    2.79
     predecessors
    2.75
    Activations Density 0.583%

    No Known Activations