© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 7720
    Prev
    Next
    INDEX
    Explanations

    words related to anticipation or excitement

    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
    0:0.03
    1:0.05
    2:0.07
    3:0.21
    4:0.13
    5:0.04
    6:0.14
    7:0.04
    8:0.07
    9:0.05
    10:0.07
    11:0.05
    Negative Logits
    nesday
    -1.60
     autos
    -1.51
    ◼
    -1.50
    ModLoader
    -1.43
    agonist
    -1.37
    orically
    -1.34
    inarily
    -1.33
     resid
    -1.32
     inevitably
    -1.32
     unavoid
    -1.31
    POSITIVE LOGITS
     Veget
    1.37
    mite
    1.34
    Joined
    1.32
     Died
    1.30
     Melania
    1.27
     guiName
    1.24
    thia
    1.18
     flowers
    1.17
     Gets
    1.17
     Theresa
    1.16
    Activations Density 0.001%

    No Known Activations