© 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. 18847
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "as."

    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
    0:0.03
    1:0.00
    2:0.14
    3:0.05
    4:0.07
    5:0.02
    6:0.06
    7:0.20
    8:0.05
    9:0.03
    10:0.17
    11:0.12
    Negative Logits
     Auditor
    -1.70
     moderator
    -1.62
     Simulator
    -1.57
     Introdu
    -1.54
     administ
    -1.53
     usher
    -1.52
     Dialogue
    -1.52
     Manager
    -1.51
     Govern
    -1.50
     stewards
    -1.50
    POSITIVE LOGITS
     sidx
    2.27
    conn
    1.95
     sqor
    1.90
    ousands
    1.79
    ortality
    1.78
    iably
    1.76
    undreds
    1.75
     batches
    1.75
     deaths
    1.74
     stockp
    1.73
    Activations Density 0.001%

    No Known Activations