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

    Neuronpedia

    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. 10778
    Prev
    Next
    INDEX
    Explanations

    terms associated with scientific discovery and investigation

    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
    0:0.03
    1:0.04
    2:0.12
    3:0.03
    4:0.02
    5:0.04
    6:0.06
    7:0.06
    8:0.31
    9:0.11
    10:0.06
    11:0.06
    Negative Logits
     seiz
    -1.42
     glim
    -1.41
     conclud
    -1.38
     trave
    -1.37
     arrang
    -1.25
    ktop
    -1.25
     Inher
    -1.22
    Appearance
    -1.14
     Tent
    -1.14
     Franç
    -1.14
    POSITIVE LOGITS
    rompt
    1.39
    icum
    1.39
    zech
    1.32
    sever
    1.24
    oops
    1.23
    uters
    1.23
    edly
    1.23
    caliber
    1.22
    pages
    1.22
    ona
    1.21
    Activations Density 0.045%

    No Known Activations