© 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. 5-ATT-KK
    11. 19498
    Prev
    Next
    INDEX
    Explanations

    phrases involving time-related conditions or delays

    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
    0:0.02
    1:0.02
    2:0.07
    3:0.13
    4:0.22
    5:0.04
    6:0.10
    7:0.11
    8:0.05
    9:0.03
    10:0.07
    11:0.10
    Negative Logits
    urally
    -1.61
    iton
    -1.52
    ording
    -1.49
    incial
    -1.43
    itant
    -1.42
    ural
    -1.41
    ctive
    -1.41
    inguished
    -1.38
    lycer
    -1.37
    uner
    -1.37
    POSITIVE LOGITS
    yip
    1.57
    soDeliveryDate
    1.40
    Newsletter
    1.39
    pez
    1.38
    rams
    1.37
    icals
    1.36
     Pax
    1.34
    rade
    1.33
    ét
    1.33
    Loading
    1.32
    Activations Density 0.003%

    No Known Activations