© 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. 5-ATT-KK
    11. 19686
    Prev
    Next
    INDEX
    Explanations

    present continuous tense verbs and phrases indicating actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.07
    3:0.06
    4:0.11
    5:0.02
    6:0.07
    7:0.44
    8:0.03
    9:0.04
    10:0.06
    11:0.02
    Negative Logits
    aires
    -1.90
    omal
    -1.66
     Cheong
    -1.66
     Videos
    -1.63
    avery
    -1.62
    lore
    -1.61
    redd
    -1.61
     Huck
    -1.60
    onyms
    -1.54
    SPONSORED
    -1.52
    POSITIVE LOGITS
     renewal
    1.98
     evacuation
    1.97
     contingency
    1.96
     conting
    1.90
     preparations
    1.90
     embark
    1.88
     deployment
    1.74
     prepar
    1.70
     ready
    1.69
     anticipation
    1.69
    Activations Density 0.001%

    No Known Activations