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. 7750
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and associated sports teams

    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
    0:0.06
    1:0.03
    2:0.05
    3:0.05
    4:0.04
    5:0.06
    6:0.31
    7:0.03
    8:0.07
    9:0.19
    10:0.03
    11:0.02
    Negative Logits
     Neville
    -3.75
     Mum
    -3.28
    Mah
    -3.28
     Freddy
    -3.27
     Na
    -3.25
     Ta
    -3.24
     Vive
    -3.23
    uka
    -3.23
     Kahn
    -3.18
     Nu
    -3.15
    POSITIVE LOGITS
     Coast
    8.50
     coast
    7.14
     coasts
    6.06
     Coastal
    5.77
     Shore
    5.76
     coastline
    5.55
     coastal
    5.44
     shore
    5.38
     Ocean
    5.23
    Ocean
    4.96
    Activations Density 0.003%

    No Known Activations