© 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. 17166
    Prev
    Next
    INDEX
    Explanations

    terms related to message processing and subscription systems

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.15
    1:0.04
    2:0.06
    3:0.09
    4:0.08
    5:0.02
    6:0.16
    7:0.14
    8:0.03
    9:0.04
    10:0.08
    11:0.06
    Negative Logits
     Hermes
    -3.00
     Boeing
    -2.69
    ace
    -2.67
     Administrator
    -2.64
    chwitz
    -2.57
     DACA
    -2.43
     Glover
    -2.41
     Cancel
    -2.40
     Dream
    -2.38
    eus
    -2.34
    POSITIVE LOGITS
     pub
    6.95
     pubs
    5.13
     Pub
    5.10
    Pub
    4.96
    pub
    4.96
     bartender
    3.66
     pint
    3.51
     tavern
    3.34
     Guinness
    3.22
     drinkers
    3.21
    Activations Density 0.008%

    No Known Activations