© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 2745
    Prev
    Next
    INDEX
    Explanations

    phrases related to noteworthy achievements or announcements, particularly in the context of racing or sports

    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
    0:0.21
    1:0.03
    2:0.06
    3:0.06
    4:0.03
    5:0.05
    6:0.04
    7:0.05
    8:0.29
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
    Indiana
    -3.68
     Cele
    -3.64
     Maine
    -3.45
     Indiana
    -3.44
     Maryland
    -3.39
    aukee
    -3.37
     Vaughn
    -3.31
    itaire
    -3.27
    Utah
    -3.27
     USC
    -3.20
    POSITIVE LOGITS
    wei
    3.11
     Yang
    2.88
     Liquid
    2.88
     tyres
    2.76
    shit
    2.73
     Qiao
    2.70
     Rampage
    2.69
     Toro
    2.67
     Dynamo
    2.61
     Bai
    2.55
    Activations Density 0.004%

    No Known Activations