© 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. 43760
    Prev
    Next
    INDEX
    Explanations

    references to online identities or specific usernames

    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
    0:0.17
    1:0.14
    2:0.07
    3:0.09
    4:0.03
    5:0.11
    6:0.03
    7:0.03
    8:0.11
    9:0.08
    10:0.05
    11:0.05
    Negative Logits
    bay
    -1.90
    payers
    -1.76
    iverse
    -1.62
    kiss
    -1.61
    bike
    -1.61
    lif
    -1.58
    file
    -1.58
    pour
    -1.58
    775
    -1.57
    clone
    -1.52
    POSITIVE LOGITS
    rocal
    1.90
    ENE
    1.85
     Contra
    1.73
     Miscellaneous
    1.73
    otine
    1.70
     Sap
    1.70
     Span
    1.66
     Wasserman
    1.59
     Introduction
    1.58
    ggle
    1.58
    Activations Density 0.002%

    No Known Activations