© 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. 10733
    Prev
    Next
    INDEX
    Explanations

    numerals and their relations in the context of actions or outcomes

    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
    0:0.04
    1:0.03
    2:0.03
    3:0.03
    4:0.05
    5:0.06
    6:0.05
    7:0.04
    8:0.02
    9:0.10
    10:0.03
    11:0.47
    Negative Logits
    eway
    -2.62
     Gallery
    -2.46
     systems
    -2.42
     Network
    -2.42
     networks
    -2.37
     Interpret
    -2.36
     History
    -2.35
     network
    -2.33
     Relations
    -2.33
     Systems
    -2.32
    POSITIVE LOGITS
     bombshell
    3.71
     bombs
    3.30
     mustard
    2.95
     bomb
    2.75
     slurs
    2.56
     drops
    2.42
    acus
    2.39
     sidx
    2.38
     needle
    2.35
     hints
    2.32
    Activations Density 0.028%

    No Known Activations