© 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. 15387
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviation sequences

    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
    0:0.02
    1:0.03
    2:0.17
    3:0.05
    4:0.09
    5:0.32
    6:0.02
    7:0.04
    8:0.04
    9:0.16
    10:0.01
    11:0.02
    Negative Logits
    andum
    -2.95
    accompan
    -2.93
    .}
    -2.70
    :[
    -2.62
     este
    -2.61
    ichever
    -2.50
     sought
    -2.49
     either
    -2.46
     divides
    -2.44
     dividing
    -2.40
    POSITIVE LOGITS
    twitter
    2.89
    pic
    2.86
     pic
    2.80
    nova
    2.77
     srfAttach
    2.76
    UGH
    2.43
    Advertisements
    2.43
    chan
    2.42
     Pastebin
    2.41
    Mom
    2.40
    Activations Density 0.003%

    No Known Activations