Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 27476
    Prev
    Next
    INDEX
    Explanations

    mentions of romantic or sexual relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.06
    3:0.08
    4:0.12
    5:0.03
    6:0.03
    7:0.27
    8:0.03
    9:0.03
    10:0.18
    11:0.08
    Negative Logits
    ////////
    -1.71
    icter
    -1.59
     matchup
    -1.53
     concise
    -1.51
    ¯¯
    -1.48
    Clear
    -1.47
    ////////////////
    -1.45
    unders
    -1.45
    auntlet
    -1.44
    ampions
    -1.43
    POSITIVE LOGITS
     uranium
    1.48
     Meg
    1.38
    Lago
    1.35
     Kare
    1.34
     rumors
    1.33
     Twice
    1.30
     Malfoy
    1.29
     666
    1.29
     Freddie
    1.28
     favors
    1.27
    Activations Density 0.001%

    No Known Activations