© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 11034
    Prev
    Next
    INDEX
    Explanations

    verbs related to management, motivation, and creative processes

    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
    0:0.06
    1:0.04
    2:0.13
    3:0.04
    4:0.03
    5:0.06
    6:0.08
    7:0.05
    8:0.19
    9:0.13
    10:0.09
    11:0.05
    Negative Logits
     Coast
    -1.11
    vals
    -1.07
    cens
    -1.04
    alos
    -1.04
    Ott
    -1.04
    birth
    -1.03
    patch
    -1.02
    hai
    -1.01
    anc
    -1.01
    Winged
    -0.99
    POSITIVE LOGITS
     efficiently
    1.62
     extensively
    1.38
     effectively
    1.27
    successfully
    1.26
    creen
    1.17
     effortlessly
    1.15
     clipboard
    1.13
     successfully
    1.12
     systematically
    1.12
    ocally
    1.11
    Activations Density 0.059%

    No Known Activations