© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 40444
    Prev
    Next
    INDEX
    Explanations

    expressions of attraction and flirtation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.05
    1:0.02
    2:0.06
    3:0.20
    4:0.05
    5:0.07
    6:0.04
    7:0.03
    8:0.06
    9:0.13
    10:0.13
    11:0.11
    Negative Logits
    utterstock
    -1.40
    rupal
    -1.36
    20439
    -1.32
    ixel
    -1.31
    ��
    -1.31
    stract
    -1.30
    eatured
    -1.27
    incinn
    -1.27
     Scal
    -1.20
    isu
    -1.19
    POSITIVE LOGITS
    ..."
    2.88
    -"
    2.71
    …"
    2.70
     …"
    2.54
    ?"
    2.49
    —"
    2.49
    !"
    2.39
    ?!"
    2.28
    ..."
    2.26
    !?"
    2.24
    Activations Density 0.271%

    No Known Activations