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

    Neuronpedia

    APICircuit 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. 7693
    Prev
    Next
    INDEX
    Explanations

    references to political and social structures or events

    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
    0:0.05
    1:0.01
    2:0.07
    3:0.31
    4:0.02
    5:0.12
    6:0.02
    7:0.05
    8:0.04
    9:0.02
    10:0.20
    11:0.02
    Negative Logits
    inventoryQuantity
    -2.21
    limits
    -2.13
     inconsistency
    -2.06
     limits
    -2.03
     limit
    -2.00
     bluntly
    -1.95
     plainly
    -1.94
    brainer
    -1.91
     constraint
    -1.90
     parentheses
    -1.88
    POSITIVE LOGITS
     pioneers
    2.05
    ortium
    1.96
     crafts
    1.94
     Wildcats
    1.87
     Lebanese
    1.85
     settlers
    1.82
     Folk
    1.81
     inventions
    1.80
     Palestin
    1.79
     multinational
    1.78
    Activations Density 0.092%

    No Known Activations