© 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. 9-ATT-KK
    11. 2011
    Prev
    Next
    INDEX
    Explanations

    specific instances or references to the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.04
    2:0.08
    3:0.06
    4:0.07
    5:0.06
    6:0.23
    7:0.02
    8:0.04
    9:0.18
    10:0.02
    11:0.05
    Negative Logits
     Minion
    -3.90
     Mack
    -3.61
     Turk
    -3.60
     Mick
    -3.46
    dylib
    -3.45
     Lambert
    -3.23
     Mushroom
    -3.21
     Loki
    -3.15
     Flag
    -3.06
     Peg
    -3.05
    POSITIVE LOGITS
     court
    5.75
     Court
    5.59
    court
    5.26
     COURT
    5.06
     courts
    5.00
     justices
    4.93
    Court
    4.89
     judicial
    4.64
     judges
    4.64
     Courts
    4.59
    Activations Density 0.035%

    No Known Activations