© 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. 3-ATT-KK
    11. 12862
    Prev
    Next
    INDEX
    Explanations

    phrases related to romantic relationships

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases and expressions related to love and affection across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.03
    3:0.35
    4:0.01
    5:0.02
    6:0.06
    7:0.17
    8:0.05
    9:0.06
    10:0.06
    11:0.11
    Negative Logits
    Loading
    -1.54
    OUGH
    -1.33
    ottest
    -1.31
    ulhu
    -1.28
    legraph
    -1.27
    itu
    -1.26
    atform
    -1.26
    将
    -1.25
    ecause
    -1.24
    版
    -1.23
    POSITIVE LOGITS
     Spartans
    1.42
    eton
    1.39
     companions
    1.37
    aukee
    1.37
     solitude
    1.34
     dwarves
    1.29
     girlfriends
    1.19
     virginity
    1.17
    cel
    1.16
     spont
    1.15
    Activations Density 0.019%

    No Known Activations