© 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. 9107
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant statistics or metrics often in a quantitative context

    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
    1:0.07
    2:0.18
    3:0.23
    4:0.02
    5:0.03
    6:0.05
    7:0.07
    8:0.13
    9:0.05
    10:0.04
    11:0.04
    Negative Logits
     servicing
    -1.45
    merce
    -1.45
     condem
    -1.37
     Palestin
    -1.37
    nings
    -1.34
     welf
    -1.32
    uploads
    -1.29
     satell
    -1.27
    kish
    -1.26
    plugins
    -1.26
    POSITIVE LOGITS
     istg
    1.60
    ️
    1.58
    lycer
    1.36
    ashtra
    1.34
    �
    1.17
    ּ
    1.17
    女
    1.17
    owder
    1.15
     Veil
    1.13
     Marketable
    1.11
    Activations Density 0.013%

    No Known Activations