© 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. 35179
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to government officials and historical figures

    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
    2:0.11
    3:0.10
    4:0.30
    5:0.03
    6:0.04
    7:0.10
    8:0.03
    9:0.03
    10:0.08
    11:0.08
    Negative Logits
     nonetheless
    -1.84
    idav
    -1.73
     Accessed
    -1.73
    annot
    -1.65
     characteristic
    -1.64
     nevertheless
    -1.59
    itionally
    -1.59
     neatly
    -1.58
    achev
    -1.55
    ographically
    -1.54
    POSITIVE LOGITS
     Hogan
    1.72
     heights
    1.66
     settlements
    1.62
     clients
    1.61
     Clintons
    1.56
     Commerce
    1.54
     Starr
    1.52
     campaigns
    1.52
    ricanes
    1.50
    ukemia
    1.48
    Activations Density 0.003%

    No Known Activations