© 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. 15286
    Prev
    Next
    INDEX
    Explanations

    quantifiers and modifiers related to quantity and identity

    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
    0:0.24
    1:0.06
    2:0.06
    3:0.07
    4:0.06
    5:0.04
    6:0.07
    7:0.08
    8:0.04
    9:0.06
    10:0.09
    11:0.06
    Negative Logits
     Marino
    -3.61
     Wolverine
    -3.49
     Boone
    -3.48
     Lash
    -3.44
     Cele
    -3.34
     Jenner
    -3.31
     Kitty
    -3.30
     McCoy
    -3.22
     Gore
    -3.15
     Siber
    -3.05
    POSITIVE LOGITS
     Sounders
    3.53
     Earthqu
    3.52
     Parables
    3.43
    Seattle
    3.30
    opsis
    3.22
     baker
    3.11
     Urug
    3.08
    ı
    3.05
     bakery
    3.04
    Bee
    3.04
    Activations Density 0.000%

    No Known Activations