© 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. 9-ATT-KK
    11. 5425
    Prev
    Next
    INDEX
    Explanations

    references to Wikipedia and its editorial processes

    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
    0:0.31
    1:0.01
    2:0.14
    3:0.08
    4:0.02
    5:0.11
    6:0.04
    7:0.04
    8:0.08
    9:0.06
    10:0.03
    11:0.02
    Negative Logits
     Ballistic
    -2.69
     packing
    -2.66
     Bethlehem
    -2.65
     LTE
    -2.53
     halftime
    -2.52
    etooth
    -2.50
     beads
    -2.46
    rolet
    -2.45
     salsa
    -2.41
     antenna
    -2.40
    POSITIVE LOGITS
     edits
    5.67
     Wikipedia
    5.34
     edit
    5.18
     Wik
    5.13
     wik
    4.91
     encyclopedia
    4.82
     wiki
    4.63
    Wikipedia
    4.60
     Wikimedia
    4.54
    Wiki
    4.48
    Activations Density 0.047%

    No Known Activations