© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43563
    Prev
    Next
    INDEX
    Explanations

    phrases related to oaths and official titles

    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
    0:0.03
    1:0.02
    2:0.11
    3:0.08
    4:0.14
    5:0.03
    6:0.06
    7:0.22
    8:0.03
    9:0.04
    10:0.10
    11:0.09
    Negative Logits
    xual
    -1.38
    soType
    -1.36
    VC
    -1.34
    Rap
    -1.29
    TPS
    -1.28
    catentry
    -1.25
     disadvantage
    -1.24
    tips
    -1.24
    cest
    -1.24
     disadvantages
    -1.24
    POSITIVE LOGITS
    schild
    1.38
     certific
    1.38
     oath
    1.33
     ceremon
    1.31
     hereby
    1.28
    without
    1.27
    wagen
    1.24
    uno
    1.24
     Sanford
    1.23
     anew
    1.22
    Activations Density 0.000%

    No Known Activations