© 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. 11170
    Prev
    Next
    INDEX
    Explanations

    phrases expressing anticipation or eagerness about future events

    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
    0:0.01
    1:0.03
    2:0.11
    3:0.24
    4:0.01
    5:0.03
    6:0.04
    7:0.08
    8:0.04
    9:0.16
    10:0.08
    11:0.11
    Negative Logits
    ulhu
    -1.45
    hs
    -1.36
    Ph
    -1.33
    eeks
    -1.28
    cyl
    -1.28
    Union
    -1.26
     guiIcon
    -1.26
    Strength
    -1.24
    Bot
    -1.23
     Sherman
    -1.23
    POSITIVE LOGITS
     adjourn
    1.47
     toile
    1.32
     spiritually
    1.31
    �
    1.30
     サ
    1.29
    stadt
    1.22
     Bahamas
    1.22
     continual
    1.21
     reven
    1.18
     nostalg
    1.17
    Activations Density 0.004%

    No Known Activations