© 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. 14353
    Prev
    Next
    INDEX
    Explanations

    video-related prompts, such as Click to play or Video Loading

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

    phrases related to video content and interactions

    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
    1:0.11
    2:0.07
    3:0.08
    4:0.03
    5:0.06
    6:0.10
    7:0.11
    8:0.09
    9:0.10
    10:0.10
    11:0.09
    Negative Logits
    govtrack
    -1.32
    orically
    -1.25
    icably
    -1.17
    imilar
    -1.09
    arton
    -1.07
    phe
    -1.04
     Historically
    -1.04
    negie
    -1.01
    asca
    -1.00
    zhen
    -1.00
    POSITIVE LOGITS
     unlocks
    1.25
     IMAGES
    1.11
     Malays
    1.07
    idav
    1.04
    MAL
    1.00
     button
    1.00
     controls
    1.00
     Emir
    0.99
    !'
    0.98
     Mahjong
    0.97
    Activations Density 0.000%

    No Known Activations