© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 20640
    Prev
    Next
    INDEX
    Explanations

    references to studies or comparisons involving Kansas

    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
    0:0.21
    1:0.06
    2:0.07
    3:0.09
    4:0.05
    5:0.04
    6:0.07
    7:0.08
    8:0.02
    9:0.06
    10:0.13
    11:0.07
    Negative Logits
    atown
    -3.76
     LAPD
    -3.71
     ----
    -3.60
    ertodd
    -3.42
     jew
    -3.41
     CCP
    -3.40
     Malays
    -3.38
     Tacoma
    -3.28
     Lakers
    -3.27
    Howard
    -3.25
    POSITIVE LOGITS
     pancreat
    7.43
     panc
    6.93
     Panc
    6.05
     insulin
    5.08
     pancakes
    5.07
     glucose
    4.58
     diabetic
    4.39
     β
    4.09
     Diabetes
    3.94
     beta
    3.71
    Activations Density 0.001%

    No Known Activations