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

    Neuronpedia

    Jacobian LensNEW
    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. 1149
    Prev
    Next
    INDEX
    Explanations

    references to institutions and organizations based in Massachusetts, particularly in the education and healthcare sectors

    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
    0:0.04
    1:0.02
    2:0.06
    3:0.07
    4:0.02
    5:0.05
    6:0.04
    7:0.02
    8:0.54
    9:0.04
    10:0.02
    11:0.02
    Negative Logits
    oglu
    -4.95
     PKK
    -4.41
    Turkish
    -4.16
    Mex
    -4.09
    Turkey
    -4.01
     Zap
    -3.97
     Azerbai
    -3.93
     Azerbaijan
    -3.90
    ğ
    -3.87
     Bolivia
    -3.84
    POSITIVE LOGITS
     Massachusetts
    7.76
     Worcester
    7.04
    Boston
    6.48
     Suffolk
    6.37
     Boston
    6.26
     Lowell
    6.03
     Rhode
    5.83
    achusetts
    5.67
     Connecticut
    5.59
     Dartmouth
    5.29
    Activations Density 0.203%

    No Known Activations