© 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. 16197
    Prev
    Next
    INDEX
    Explanations

    references to specific people, particularly in the context of medical or procedural situations

    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
    0:0.26
    1:0.06
    2:0.09
    3:0.03
    4:0.03
    5:0.01
    6:0.05
    7:0.12
    8:0.02
    9:0.02
    10:0.21
    11:0.04
    Negative Logits
     Meier
    -3.66
     Sloven
    -3.65
     Lavrov
    -3.50
     Slovenia
    -3.46
    Minnesota
    -3.38
     Finnish
    -3.38
     Everest
    -3.35
    Sov
    -3.34
     Gork
    -3.26
     Sov
    -3.23
    POSITIVE LOGITS
     Bat
    10.81
    Bat
    9.88
     bat
    7.72
    BAT
    6.47
     BAT
    6.36
    bat
    6.31
     bats
    6.23
     Batman
    5.84
    Batman
    5.80
    bats
    5.60
    Activations Density 0.014%

    No Known Activations