© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 18507
    Prev
    Next
    INDEX
    Explanations

    specific transactional and basketball-related terms

    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
    0:0.09
    1:0.02
    2:0.08
    3:0.06
    4:0.10
    5:0.05
    6:0.18
    7:0.06
    8:0.13
    9:0.11
    10:0.02
    11:0.05
    Negative Logits
    flag
    -3.54
    scan
    -3.26
    Dog
    -3.23
    rador
    -3.18
    \/
    -3.12
    ploma
    -3.01
    ó
    -2.99
    admin
    -2.97
    olkien
    -2.97
    Í
    -2.83
    POSITIVE LOGITS
     NBA
    5.33
     Grizzlies
    5.12
     Cavs
    5.11
     Pacers
    5.00
     Nuggets
    4.79
     Basketball
    4.76
     Pelicans
    4.70
     Hornets
    4.69
     Lakers
    4.68
    NBA
    4.62
    Activations Density 0.088%

    No Known Activations