© 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. 8046
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal events or ceremonies

    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
    0:0.08
    1:0.09
    2:0.06
    3:0.03
    4:0.20
    5:0.12
    6:0.05
    7:0.04
    8:0.07
    9:0.07
    10:0.08
    11:0.06
    Negative Logits
    apixel
    -1.72
     reader
    -1.46
     wont
    -1.43
    elaide
    -1.42
     smart
    -1.40
    EEEE
    -1.37
    cedented
    -1.35
     rider
    -1.34
     ourselves
    -1.33
    priv
    -1.32
    POSITIVE LOGITS
     viz
    1.69
    uberty
    1.66
     ⓘ
    1.47
     Pu
    1.46
     Mig
    1.42
     namely
    1.40
     Initially
    1.40
     Suc
    1.40
     Trog
    1.39
    uled
    1.38
    Activations Density 0.053%

    No Known Activations