© 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. 14385
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences about specific events, activities, or issues

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases that indicate personal or emotional connections between individuals and their experiences

    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
    2:0.19
    3:0.09
    4:0.01
    5:0.04
    6:0.06
    7:0.11
    8:0.18
    9:0.07
    10:0.08
    11:0.06
    Negative Logits
     Yose
    -0.95
    vous
    -0.94
     Osw
    -0.90
    govtrack
    -0.89
    ワ
    -0.87
    elcome
    -0.84
    rences
    -0.84
    grave
    -0.83
     Pirates
    -0.82
    shown
    -0.81
    POSITIVE LOGITS
     standpoint
    0.91
     persuasion
    0.85
    ipedia
    0.82
     strap
    0.81
     shelf
    0.77
     manufacture
    0.76
     periphery
    0.76
    storage
    0.76
    times
    0.75
    Manufact
    0.73
    Activations Density 0.123%

    No Known Activations