© 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. 3-ATT-KK
    11. 10860
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" with varying frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.03
    2:0.18
    3:0.23
    4:0.02
    5:0.03
    6:0.05
    7:0.08
    8:0.06
    9:0.07
    10:0.13
    11:0.05
    Negative Logits
     immersion
    -1.03
    amba
    -0.98
     undisclosed
    -0.97
     Hum
    -0.95
    ecast
    -0.94
    nants
    -0.94
     concess
    -0.93
     Mazda
    -0.92
     phon
    -0.90
     Kits
    -0.90
    POSITIVE LOGITS
    aea
    1.19
    Article
    1.14
    NetMessage
    1.12
    sted
    1.09
    igen
    1.06
     stitches
    1.03
    igion
    1.03
     })
    1.02
    stocks
    1.02
    enegger
    1.00
    Activations Density 0.022%

    No Known Activations