© 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. 44041
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and organizations

    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
    1:0.03
    2:0.07
    3:0.15
    4:0.36
    5:0.04
    6:0.04
    7:0.03
    8:0.05
    9:0.05
    10:0.06
    11:0.04
    Negative Logits
    wcs
    -1.99
    alties
    -1.84
    notation
    -1.72
    chwitz
    -1.67
    artifacts
    -1.65
     hasn
    -1.64
    istries
    -1.60
    sites
    -1.59
     fixtures
    -1.58
     weren
    -1.57
    POSITIVE LOGITS
     Osw
    1.81
     (@
    1.63
     Wend
    1.57
     commenter
    1.52
     rhet
    1.48
     Krish
    1.48
     Psych
    1.46
     theolog
    1.44
     Ov
    1.44
     Shutterstock
    1.43
    Activations Density 0.042%

    No Known Activations