© 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. 9-ATT-KK
    11. 3423
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate certainty or absoluteness in a statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.03
    3:0.10
    4:0.02
    5:0.04
    6:0.02
    7:0.03
    8:0.04
    9:0.02
    10:0.18
    11:0.41
    Negative Logits
     americ
    -2.99
     didnt
    -2.91
     dont
    -2.75
     alot
    -2.73
       
    -2.71
      
    -2.70
     doesnt
    -2.69
     independ
    -2.66
            
    -2.62
    ↵ 
    -2.61
    POSITIVE LOGITS
    ,
    3.22
    —"
    3.05
    -,
    2.86
    ?,
    2.84
    —
    2.62
    ,[
    2.62
     ("
    2.58
    ,—
    2.56
     —
    2.38
    ;
    2.34
    Activations Density 0.021%

    No Known Activations