© 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. 9-ATT-KK
    11. 1123
    Prev
    Next
    INDEX
    Explanations

    references to economic or material wealth

    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
    1:0.02
    2:0.12
    3:0.05
    4:0.04
    5:0.06
    6:0.03
    7:0.04
    8:0.44
    9:0.03
    10:0.04
    11:0.02
    Negative Logits
    Detroit
    -4.89
     Toledo
    -4.13
     Detroit
    -4.04
     Lansing
    -3.98
    Michigan
    -3.89
     Pistons
    -3.87
    Baltimore
    -3.81
     Louisville
    -3.75
     Akron
    -3.74
     Cleveland
    -3.55
    POSITIVE LOGITS
     PNG
    5.47
     Fiji
    5.40
     NZ
    5.31
     Australians
    5.29
     Indonesian
    5.17
     Papua
    5.15
     Australian
    4.97
     Kiw
    4.85
     Australia
    4.83
     Canberra
    4.80
    Activations Density 0.007%

    No Known Activations