© 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. 10-ATT-KK
    11. 17448
    Prev
    Next
    INDEX
    Explanations

    mentions of social media handles and their related contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.15
    1:0.10
    2:0.11
    3:0.07
    4:0.03
    5:0.02
    6:0.12
    7:0.08
    8:0.02
    9:0.06
    10:0.16
    11:0.03
    Negative Logits
     actionGroup
    -3.64
    anooga
    -3.53
     Merchants
    -3.14
     omn
    -3.04
    adal
    -3.01
    LCS
    -2.95
     Opera
    -2.88
    otiation
    -2.82
    ammed
    -2.81
    Merc
    -2.81
    POSITIVE LOGITS
     Shawn
    8.56
     Sioux
    4.13
     Shay
    3.79
    Sh
    3.49
     Kane
    3.39
     Mush
    3.29
     Cory
    3.23
     Chero
    3.22
     Shane
    3.21
     Owen
    3.16
    Activations Density 0.001%

    No Known Activations