© 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. 5-ATT-KK
    11. 21703
    Prev
    Next
    INDEX
    Explanations

    phrases that reflect inquiry or questioning

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.32
    1:0.14
    2:0.03
    3:0.04
    4:0.03
    5:0.09
    6:0.03
    7:0.02
    8:0.10
    9:0.07
    10:0.04
    11:0.03
    Negative Logits
    neau
    -1.78
    sson
    -1.72
    theless
    -1.70
     puck
    -1.61
    etheless
    -1.60
     ware
    -1.53
    plex
    -1.53
     linem
    -1.50
    grain
    -1.49
    sole
    -1.48
    POSITIVE LOGITS
     What
    2.46
     How
    2.43
     Whats
    2.36
     Submit
    2.24
     Explain
    2.23
     Desc
    2.21
     Does
    2.18
    How
    2.17
    What
    2.13
     Did
    2.10
    Activations Density 0.041%

    No Known Activations