© 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. 5-ATT-KK
    11. 9376
    Prev
    Next
    INDEX
    Explanations

    references to authority and directives related to individuals or groups

    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
    1:0.01
    2:0.04
    3:0.05
    4:0.21
    5:0.03
    6:0.02
    7:0.43
    8:0.02
    9:0.03
    10:0.05
    11:0.05
    Negative Logits
     excuse
    -1.47
    aea
    -1.46
    du
    -1.42
     rarity
    -1.39
     coincidence
    -1.38
     ankles
    -1.38
    cation
    -1.37
    aucuses
    -1.37
    bek
    -1.34
     suscept
    -1.34
    POSITIVE LOGITS
     directing
    2.23
     toward
    1.90
     directed
    1.87
     redirected
    1.80
     towards
    1.68
     directions
    1.64
     DIRECT
    1.63
     direction
    1.61
     Marketing
    1.57
     directs
    1.54
    Activations Density 0.016%

    No Known Activations