© 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. 20899
    Prev
    Next
    INDEX
    Explanations

    references to locations and sensory experiences related to food and spice

    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
    0:0.16
    1:0.06
    2:0.05
    3:0.11
    4:0.04
    5:0.02
    6:0.08
    7:0.14
    8:0.02
    9:0.06
    10:0.16
    11:0.06
    Negative Logits
     Sabres
    -3.06
     Guant
    -2.89
     macOS
    -2.76
     Peg
    -2.76
     Yosemite
    -2.72
     Jordanian
    -2.66
     Abby
    -2.65
     Becky
    -2.62
    ylan
    -2.62
    querque
    -2.58
    POSITIVE LOGITS
     Chennai
    7.35
     Tamil
    5.59
     Bangalore
    4.32
     Nadu
    4.00
     Tir
    3.80
     Sri
    3.79
     Kerala
    3.66
     Hyder
    3.65
     Mumbai
    3.57
     Sanskrit
    3.46
    Activations Density 0.001%

    No Known Activations