© 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. 9-ATT-KK
    11. 4174
    Prev
    Next
    INDEX
    Explanations

    references to personal beliefs and experiences

    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
    0:0.07
    1:0.03
    2:0.05
    3:0.02
    4:0.06
    5:0.03
    6:0.20
    7:0.05
    8:0.06
    9:0.34
    10:0.01
    11:0.02
    Negative Logits
     Crane
    -4.06
     Hardy
    -3.86
     Bond
    -3.82
     ATI
    -3.70
     humid
    -3.70
     Wyr
    -3.60
     Viz
    -3.58
     Rhodes
    -3.47
     Sunni
    -3.47
     Tehran
    -3.46
    POSITIVE LOGITS
     Jo
    7.98
    Jo
    7.86
     Joel
    7.07
    jo
    6.75
    JO
    6.44
     JO
    6.04
     jo
    5.48
     Jos
    4.97
     Joan
    4.70
    ipel
    4.53
    Activations Density 0.006%

    No Known Activations