© 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. 14509
    Prev
    Next
    INDEX
    Explanations

    mentions of places or locations like towns, cities, or counties

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

    terms related to significant events or topics in various contexts, particularly those involving cases, campaigns, or public matters

    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
    0:0.03
    1:0.03
    2:0.13
    3:0.04
    4:0.02
    5:0.04
    6:0.38
    7:0.07
    8:0.06
    9:0.03
    10:0.05
    11:0.05
    Negative Logits
    ospels
    -1.24
    icans
    -1.13
    ocket
    -1.08
    orate
    -1.07
    clave
    -1.05
    minist
    -1.02
    gemony
    -0.98
     Library
    -0.98
    ican
    -0.96
    ords
    -0.96
    POSITIVE LOGITS
    Stretch
    1.06
    Apply
    1.01
     HIT
    1.00
    quickShipAvailable
    0.97
    BuyableInstoreAndOnline
    0.92
     surpr
    0.92
     SUM
    0.90
     SAL
    0.90
    ificial
    0.90
    龍�
    0.89
    Activations Density 0.491%

    No Known Activations