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

    Neuronpedia

    Jacobian LensNEW
    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. 10-ATT-KK
    11. 8538
    Prev
    Next
    INDEX
    Explanations

    mentions of Cincinnati and its local entities, particularly in the context of sports and community events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.30
    1:0.03
    2:0.03
    3:0.05
    4:0.02
    5:0.03
    6:0.08
    7:0.15
    8:0.01
    9:0.04
    10:0.18
    11:0.03
    Negative Logits
     Stockholm
    -4.16
     Greenland
    -3.98
     Emir
    -3.96
     SAP
    -3.80
     McKay
    -3.67
     Sharks
    -3.66
     Sweden
    -3.61
     Antarctica
    -3.60
     Swedish
    -3.53
     Sands
    -3.51
    POSITIVE LOGITS
     Cincinnati
    7.83
     Bengals
    7.80
    incinnati
    4.82
     Giov
    4.82
     Reds
    4.45
     Akron
    4.21
     Ohio
    4.03
     Marvin
    3.85
     Cleveland
    3.81
    Ohio
    3.79
    Activations Density 0.023%

    No Known Activations