© 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. 10-ATT-KK
    11. 14094
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases that express additional elements or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.03
    2:0.03
    3:0.04
    4:0.22
    5:0.02
    6:0.03
    7:0.15
    8:0.03
    9:0.05
    10:0.04
    11:0.25
    Negative Logits
     instances
    -2.64
     advantages
    -2.52
     failings
    -2.26
    ront
    -2.25
    Information
    -2.25
     motives
    -2.17
     disadvantages
    -2.14
     positives
    -2.12
     characteristics
    -2.06
     thefts
    -2.05
    POSITIVE LOGITS
    ド
    2.48
    adobe
    2.46
     glacier
    2.36
     kale
    2.25
     MacArthur
    2.22
     Sturgeon
    2.15
     Mehran
    2.11
     rag
    2.06
     nuts
    2.04
     canvas
    2.00
    Activations Density 0.002%

    No Known Activations