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. 13
    Prev
    Next
    INDEX
    Explanations

    references to financial policies and reports aimed at consumer protection

    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
    1:0.03
    2:0.05
    3:0.07
    4:0.04
    5:0.04
    6:0.04
    7:0.03
    8:0.40
    9:0.05
    10:0.03
    11:0.13
    Negative Logits
    .—
    -3.13
     Cleveland
    -2.92
     Engels
    -2.82
     Vik
    -2.81
     Tata
    -2.69
     Shank
    -2.68
    ventus
    -2.67
     Trotsky
    -2.66
     Ary
    -2.66
     Brah
    -2.64
    POSITIVE LOGITS
     PNG
    3.69
     Canberra
    3.67
    Topics
    3.52
    Austral
    3.38
     Queensland
    3.30
     Papua
    3.27
     Tasman
    3.17
     Brisbane
    3.04
     Indones
    3.00
     Australians
    2.95
    Activations Density 0.002%

    No Known Activations