© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 9848
    Prev
    Next
    INDEX
    Explanations

    references to speech and statements made by individuals

    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
    0:0.03
    1:0.02
    2:0.03
    3:0.07
    4:0.04
    5:0.07
    6:0.02
    7:0.05
    8:0.47
    9:0.02
    10:0.03
    11:0.11
    Negative Logits
     Milwaukee
    -4.15
     STL
    -3.76
     Fargo
    -3.75
     Zimmer
    -3.68
    Minnesota
    -3.52
     Minneapolis
    -3.49
    waukee
    -3.47
     Borg
    -3.46
     Wisconsin
    -3.43
    neapolis
    -3.43
    POSITIVE LOGITS
     Queensland
    5.94
    Australia
    5.16
     NSW
    5.15
     Australia
    4.91
     Canberra
    4.90
    Australian
    4.90
     NRL
    4.88
     Australians
    4.87
     Turnbull
    4.76
    Austral
    4.65
    Activations Density 0.044%

    No Known Activations