© 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. 9-ATT-KK
    11. 10871
    Prev
    Next
    INDEX
    Explanations

    punctuations indicating list structures or itemized information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.05
    2:0.11
    3:0.05
    4:0.07
    5:0.04
    6:0.20
    7:0.04
    8:0.05
    9:0.18
    10:0.03
    11:0.05
    Negative Logits
     Bag
    -3.84
    bag
    -3.67
     Fowler
    -3.64
     sled
    -3.58
     Fitzgerald
    -3.57
     Arabia
    -3.55
     BYU
    -3.51
     Bauer
    -3.40
     Schwe
    -3.39
    bags
    -3.33
    POSITIVE LOGITS
     Neon
    10.70
     neon
    8.50
     Neo
    4.48
    eno
    4.20
    eni
    4.16
     Sunset
    3.94
     neutron
    3.82
     Midnight
    3.80
     Nept
    3.78
    Ne
    3.77
    Activations Density 0.001%

    No Known Activations