© 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. 10701
    Prev
    Next
    INDEX
    Explanations

    numerical values or statistics related to events 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
    0:0.02
    1:0.05
    2:0.19
    3:0.11
    4:0.02
    5:0.03
    6:0.19
    7:0.07
    8:0.09
    9:0.05
    10:0.07
    11:0.05
    Negative Logits
     spoiler
    -1.40
     crop
    -1.32
    覚醒
    -1.27
     icing
    -1.26
     ster
    -1.26
     giveaway
    -1.19
     flavour
    -1.17
    PDATE
    -1.16
     feather
    -1.15
     cont
    -1.13
    POSITIVE LOGITS
    conservancy
    1.81
    bilt
    1.70
    cffff
    1.68
    zona
    1.57
    wx
    1.55
    zanne
    1.46
    zie
    1.45
    taboola
    1.45
    onte
    1.43
    ilet
    1.42
    Activations Density 0.027%

    No Known Activations