© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 12363
    Prev
    Next
    INDEX
    Explanations

    questions and trivia-related sentences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    significant quantifiers and descriptions indicating importance or value

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.11
    2:0.14
    3:0.11
    4:0.05
    5:0.03
    6:0.09
    7:0.07
    8:0.10
    9:0.09
    10:0.06
    11:0.05
    Negative Logits
    nings
    -1.36
     disadvant
    -1.29
     blat
    -1.28
     challeng
    -1.27
    alloc
    -1.21
     destro
    -1.20
    atever
    -1.20
    raints
    -1.19
     sacrific
    -1.18
    buster
    -1.16
    POSITIVE LOGITS
     Simulator
    1.20
     istg
    1.12
     Unch
    1.05
    ucha
    1.03
     ›
    1.02
    ・
    1.02
    cffffcc
    1.01
    ️
    1.01
     ‎
    1.01
     Statistics
    1.00
    Activations Density 0.033%

    No Known Activations