© 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. 481
    Prev
    Next
    INDEX
    Explanations

    references to statistical data and percentage increases in educational contexts

    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
    0:0.09
    1:0.03
    2:0.06
    3:0.05
    4:0.04
    5:0.07
    6:0.13
    7:0.05
    8:0.23
    9:0.12
    10:0.04
    11:0.02
    Negative Logits
     Kuala
    -3.49
     Bale
    -3.49
     Malays
    -3.44
    Mal
    -3.11
     Cheong
    -3.11
     Inquisition
    -3.05
    Iran
    -3.00
     Saddam
    -2.98
    Iraq
    -2.95
     Iraqi
    -2.94
    POSITIVE LOGITS
     Rochester
    9.45
    hester
    6.12
     Monroe
    5.19
     Syracuse
    4.85
     Niagara
    4.59
     Erie
    4.24
     Minneapolis
    4.17
     Buffalo
    4.09
    Minnesota
    4.07
     Albany
    3.96
    Activations Density 0.002%

    No Known Activations