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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 3252
    Prev
    Next
    INDEX
    Explanations

    negative phrases or expressions related to uncertainty and doubt

    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
    0:0.05
    1:0.39
    2:0.04
    3:0.08
    4:0.02
    5:0.07
    6:0.07
    7:0.04
    8:0.03
    9:0.08
    10:0.04
    11:0.02
    Negative Logits
    zeb
    -2.33
     chiefly
    -2.32
    emouth
    -2.23
     preferably
    -2.19
     principally
    -2.17
     mainly
    -2.12
    atory
    -2.11
    otti
    -2.09
    ook
    -2.09
     namely
    -2.08
    POSITIVE LOGITS
     decades
    3.80
     months
    3.79
     thousands
    3.72
     years
    3.65
     Months
    3.24
     dozens
    3.22
    Years
    3.21
     centuries
    3.18
     hundreds
    3.17
     weeks
    3.17
    Activations Density 0.011%

    No Known Activations