© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 38012
    Prev
    Next
    INDEX
    Explanations

    phrases that express desires or wants

    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
    0:0.02
    1:0.02
    2:0.17
    3:0.05
    4:0.14
    5:0.04
    6:0.14
    7:0.07
    8:0.17
    9:0.03
    10:0.06
    11:0.04
    Negative Logits
     ACTIONS
    -1.76
    overe
    -1.64
    uffer
    -1.59
     presence
    -1.49
     Dating
    -1.47
    ゼウス
    -1.45
    izen
    -1.42
    dq
    -1.41
     Monitoring
    -1.41
    wat
    -1.39
    POSITIVE LOGITS
     cheapest
    1.55
    iest
    1.54
     costs
    1.45
    PLA
    1.45
     backer
    1.38
    !.
    1.38
     backers
    1.38
     Canter
    1.33
    WOOD
    1.32
    EngineDebug
    1.32
    Activations Density 0.002%

    No Known Activations