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

    Neuronpedia

    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. 10-ATT-KK
    11. 15109
    Prev
    Next
    INDEX
    Explanations

    specific names and proper nouns, particularly those related to people and dates

    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
    0:0.06
    1:0.06
    2:0.03
    3:0.03
    4:0.03
    5:0.02
    6:0.03
    7:0.49
    8:0.02
    9:0.03
    10:0.11
    11:0.04
    Negative Logits
    Í
    -3.22
    NA
    -3.08
     NEO
    -3.03
     Nunes
    -2.93
     Nir
    -2.91
     Ö
    -2.86
     Ny
    -2.77
     Nad
    -2.72
    PN
    -2.69
    NN
    -2.69
    POSITIVE LOGITS
    agra
    2.89
    drive
    2.80
     Garage
    2.56
    bucks
    2.46
    beck
    2.41
    coat
    2.30
    artney
    2.28
    ache
    2.28
     Chase
    2.26
     Unloaded
    2.23
    Activations Density 0.171%

    No Known Activations