© 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. 21320
    Prev
    Next
    INDEX
    Explanations

    concepts related to dating ideas and relationships

    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
    0:0.19
    1:0.04
    2:0.05
    3:0.09
    4:0.08
    5:0.02
    6:0.17
    7:0.12
    8:0.02
    9:0.04
    10:0.04
    11:0.10
    Negative Logits
    ��
    -3.40
     pasture
    -2.83
    assembly
    -2.77
     Helm
    -2.75
     Defenders
    -2.71
     guiIcon
    -2.61
    monary
    -2.57
    hesda
    -2.56
     pul
    -2.54
     compressor
    -2.54
    POSITIVE LOGITS
     Tinder
    6.76
     dating
    5.91
     Dating
    5.82
    dating
    4.70
     monog
    4.70
     romantic
    4.44
     romance
    4.20
     singles
    4.04
     flirt
    4.00
     dates
    3.92
    Activations Density 0.040%

    No Known Activations