© 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. 21560
    Prev
    Next
    INDEX
    Explanations

    expressions indicating levels of uncertainty or caution

    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
    0:0.06
    1:0.02
    2:0.05
    3:0.34
    4:0.03
    5:0.04
    6:0.01
    7:0.04
    8:0.02
    9:0.01
    10:0.30
    11:0.02
    Negative Logits
     heroine
    -1.87
     WRITE
    -1.87
     campaigner
    -1.82
     NEWS
    -1.79
     Chronicles
    -1.77
     protector
    -1.77
    VIDEO
    -1.76
     extensively
    -1.72
     hoax
    -1.71
     gripping
    -1.71
    POSITIVE LOGITS
     expense
    3.00
     level
    2.86
     intervals
    2.85
     heights
    2.48
     discretion
    2.45
     pinnacle
    2.42
    minimum
    2.36
     whim
    2.36
    peed
    2.34
     vantage
    2.34
    Activations Density 0.325%

    No Known Activations