© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7906
    Prev
    Next
    INDEX
    Explanations

    articles and the definite article "the" that indicate nouns in the text

    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
    1:0.02
    2:0.14
    3:0.06
    4:0.08
    5:0.03
    6:0.14
    7:0.17
    8:0.07
    9:0.03
    10:0.08
    11:0.11
    Negative Logits
     VIDEOS
    -1.43
     ACTIONS
    -1.40
    龍喚士
    -1.40
    Results
    -1.36
    Products
    -1.35
    iod
    -1.33
     Fishing
    -1.29
    despite
    -1.28
    Rated
    -1.27
    Apart
    -1.26
    POSITIVE LOGITS
     whom
    1.46
    nikov
    1.37
    fork
    1.35
     wheelchair
    1.35
    oust
    1.31
    awi
    1.29
     Kingston
    1.28
     franc
    1.27
     pocket
    1.25
    agogue
    1.22
    Activations Density 0.003%

    No Known Activations