© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15688
    Prev
    Next
    INDEX
    Explanations

    phrases indicating places or locations

    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
    0:0.18
    1:0.08
    2:0.07
    3:0.06
    4:0.03
    5:0.02
    6:0.05
    7:0.11
    8:0.02
    9:0.03
    10:0.26
    11:0.03
    Negative Logits
    ��
    -3.16
    Dallas
    -3.14
    amazon
    -2.98
    Beck
    -2.97
    ascript
    -2.95
     Kirin
    -2.86
     Valencia
    -2.73
     Vega
    -2.72
    aco
    -2.70
    egu
    -2.66
    POSITIVE LOGITS
     Som
    10.22
     Somali
    5.67
     Somalia
    5.29
     som
    5.24
     SOM
    4.98
     Sar
    3.77
     Sy
    3.73
     Mog
    3.67
     Ng
    3.55
     Sym
    3.33
    Activations Density 0.003%

    No Known Activations