© 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. 10860
    Prev
    Next
    INDEX
    Explanations

    references to user feedback and survey participation related to a specific tool or community

    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
    0:0.19
    1:0.07
    2:0.09
    3:0.04
    4:0.06
    5:0.04
    6:0.09
    7:0.08
    8:0.02
    9:0.05
    10:0.18
    11:0.04
    Negative Logits
    bach
    -3.44
     GS
    -3.38
    catentry
    -3.37
    izza
    -3.07
    rera
    -2.93
    龍契士
    -2.92
    gage
    -2.90
    ensitivity
    -2.89
    Jessica
    -2.83
    Jess
    -2.79
    POSITIVE LOGITS
     Nim
    10.30
     Nab
    4.28
     Nolan
    3.98
     locom
    3.93
     Pry
    3.92
     Gob
    3.91
     Nag
    3.87
     Nuclear
    3.85
    NI
    3.79
     Neh
    3.78
    Activations Density 0.009%

    No Known Activations