© 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. 2-ATT-KK
    11. 21387
    Prev
    Next
    INDEX
    Explanations

    phrases or terms that indicate an action is being discussed, particularly in the context of writing or summarizing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.01
    2:0.12
    3:0.04
    4:0.31
    5:0.03
    6:0.02
    7:0.02
    8:0.22
    9:0.07
    10:0.04
    11:0.01
    Negative Logits
     chances
    -1.34
     brow
    -1.32
     opportunities
    -1.31
     moms
    -1.31
     opportunity
    -1.31
     sudden
    -1.25
     surprises
    -1.24
     possibilities
    -1.24
     distractions
    -1.24
     concentration
    -1.22
    POSITIVE LOGITS
    -+-+
    1.51
    ription
    1.51
    escription
    1.47
     ashore
    1.47
    ��
    1.41
     Pastebin
    1.37
     Gazette
    1.36
    Journal
    1.36
     withd
    1.33
    aiden
    1.32
    Activations Density 0.043%

    No Known Activations