© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 35043
    Prev
    Next
    INDEX
    Explanations

    words and sounds related to the theme of "entwined."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.05
    3:0.05
    4:0.05
    5:0.04
    6:0.50
    7:0.03
    8:0.04
    9:0.06
    10:0.06
    11:0.04
    Negative Logits
     weights
    -1.21
     moderation
    -1.20
    HT
    -1.18
     dipped
    -1.18
    yip
    -1.17
    afety
    -1.15
    ubi
    -1.14
     fav
    -1.13
    ModLoader
    -1.11
    inventoryQuantity
    -1.11
    POSITIVE LOGITS
     Lauder
    1.27
    RET
    1.22
    ciating
    1.18
    uries
    1.18
    abeth
    1.18
    acement
    1.16
     Rove
    1.13
    LECT
    1.12
     Kessler
    1.12
    addle
    1.11
    Activations Density 0.002%

    No Known Activations