© 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. 2657
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or conditionality regarding people or situations

    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
    0:0.21
    1:0.15
    2:0.06
    3:0.03
    4:0.04
    5:0.05
    6:0.03
    7:0.02
    8:0.18
    9:0.05
    10:0.04
    11:0.08
    Negative Logits
    pez
    -1.62
     BELOW
    -1.54
    ghan
    -1.51
    chart
    -1.50
    omers
    -1.44
    atic
    -1.43
    gall
    -1.42
     Prob
    -1.42
     Reed
    -1.42
    ajor
    -1.41
    POSITIVE LOGITS
    etc
    1.81
     upkeep
    1.58
     rebirth
    1.56
    halla
    1.49
     greet
    1.47
     Allaah
    1.47
     blah
    1.45
     traveler
    1.44
     travels
    1.43
     blu
    1.42
    Activations Density 0.013%

    No Known Activations