© 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. 3-ATT-KK
    11. 7110
    Prev
    Next
    INDEX
    Explanations

    comparative terms and descriptions of similarities and differences between concepts or entities

    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
    1:0.06
    2:0.06
    3:0.02
    4:0.05
    5:0.29
    6:0.07
    7:0.07
    8:0.04
    9:0.04
    10:0.13
    11:0.08
    Negative Logits
     externalToEVAOnly
    -1.77
    etter
    -1.59
     starving
    -1.53
    hetamine
    -1.52
    iji
    -1.51
     Goodbye
    -1.50
    otonin
    -1.50
    ESCO
    -1.50
     Frie
    -1.48
    ogo
    -1.48
    POSITIVE LOGITS
     topics
    2.27
     descriptions
    2.26
     acron
    2.23
     respective
    2.19
     themes
    2.19
     annotations
    2.17
     chronological
    2.12
     informative
    2.10
     topic
    2.09
     overarching
    2.09
    Activations Density 0.655%

    No Known Activations