© 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. 3112
    Prev
    Next
    INDEX
    Explanations

    the word "and" in various contexts

    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
    0:0.16
    1:0.02
    2:0.06
    3:0.05
    4:0.07
    5:0.03
    6:0.15
    7:0.02
    8:0.14
    9:0.07
    10:0.04
    11:0.14
    Negative Logits
    gdala
    -1.43
     裏�
    -1.41
     coded
    -1.39
     barracks
    -1.39
     addon
    -1.33
     stash
    -1.26
    chens
    -1.24
    endez
    -1.23
    meaning
    -1.22
    chen
    -1.21
    POSITIVE LOGITS
    etc
    1.77
    rawdownloadcloneembedreportprint
    1.55
     Artemis
    1.44
     Conclusion
    1.40
    CONCLUS
    1.29
    ogether
    1.27
     scissors
    1.26
    biz
    1.25
     Curiosity
    1.24
     Intellectual
    1.24
    Activations Density 0.004%

    No Known Activations