© 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. 43688
    Prev
    Next
    INDEX
    Explanations

    instances of the word "footnote" and its variations or related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    2:0.06
    3:0.06
    4:0.09
    5:0.03
    6:0.04
    7:0.36
    8:0.03
    9:0.04
    10:0.11
    11:0.07
    Negative Logits
    owler
    -1.55
    owment
    -1.52
    elf
    -1.49
    ツ
    -1.48
    ンジ
    -1.48
    hesda
    -1.46
    adelphia
    -1.44
    ggie
    -1.42
    anooga
    -1.41
    igon
    -1.40
    POSITIVE LOGITS
     footnote
    1.74
    魔
    1.49
     proceedings
    1.44
     omission
    1.43
     dates
    1.38
     agendas
    1.37
     consequential
    1.37
     events
    1.36
    cknowled
    1.32
     approving
    1.32
    Activations Density 0.001%

    No Known Activations