© 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. 7668
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to seasonal themes and community events

    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
    1:0.01
    2:0.15
    3:0.04
    4:0.27
    5:0.02
    6:0.17
    7:0.14
    8:0.02
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
    田
    -1.36
    SPONSORED
    -1.20
    starter
    -1.19
    ら
    -1.18
    Applications
    -1.16
    pled
    -1.14
    abouts
    -1.14
    prototype
    -1.14
    Trivia
    -1.13
    ファ
    -1.12
    POSITIVE LOGITS
    iem
    1.32
    icro
    1.32
     neighb
    1.25
    aila
    1.18
    ijk
    1.15
     Aless
    1.13
     Beaut
    1.12
     AUT
    1.10
     sts
    1.10
     unbeliev
    1.10
    Activations Density 0.009%

    No Known Activations