© 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. 19799
    Prev
    Next
    INDEX
    Explanations

    occurrences of significant historical events

    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
    0:0.03
    1:0.02
    2:0.04
    3:0.07
    4:0.18
    5:0.21
    6:0.05
    7:0.08
    8:0.03
    9:0.12
    10:0.03
    11:0.08
    Negative Logits
    Instead
    -3.42
     Instead
    -3.02
    didn
    -2.99
    ntil
    -2.98
     Nope
    -2.87
     whim
    -2.79
     Invalid
    -2.76
    rompt
    -2.65
     weren
    -2.63
     didnt
    -2.56
    POSITIVE LOGITS
     publishes
    3.64
     blogs
    3.11
     explores
    2.97
     internationally
    2.90
     specializing
    2.82
     contributes
    2.80
     reviews
    2.77
     focuses
    2.70
     enjoys
    2.69
     advises
    2.65
    Activations Density 0.271%

    No Known Activations