© 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. 3-ATT-KK
    11. 5496
    Prev
    Next
    INDEX
    Explanations

    illustrative phrases and arguments in relation to various topics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.01
    1:0.04
    2:0.08
    3:0.14
    4:0.02
    5:0.04
    6:0.04
    7:0.14
    8:0.10
    9:0.15
    10:0.06
    11:0.13
    Negative Logits
    �
    -1.24
     maintenance
    -1.16
    Scotland
    -1.11
     quietly
    -1.10
    �
    -1.08
    в
    -1.07
     Tanzania
    -1.04
    akia
    -1.01
     inhibitor
    -0.99
    シャ
    -0.98
    POSITIVE LOGITS
    acters
    1.23
    Spoiler
    1.16
     likeness
    1.15
     Graphic
    1.11
    tesque
    1.09
     illustrating
    1.09
    idth
    1.09
    png
    1.07
    Font
    1.06
    yrinth
    1.06
    Activations Density 0.009%

    No Known Activations