Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 8530
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that"

    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
    0:0.05
    1:0.04
    2:0.12
    3:0.05
    4:0.04
    5:0.07
    6:0.07
    7:0.08
    8:0.12
    9:0.12
    10:0.13
    11:0.05
    Negative Logits
    ersed
    -1.12
     beware
    -1.05
    etooth
    -1.02
     Wonderful
    -0.99
    eware
    -0.99
     crave
    -0.99
    ield
    -0.97
    isdom
    -0.97
    ometimes
    -0.94
     Everywhere
    -0.92
    POSITIVE LOGITS
     controvers
    1.08
    >[
    1.04
    uphem
    1.03
     "...
    0.95
     objections
    0.92
     Moreno
    0.91
    izoph
    0.89
     Dmitry
    0.89
     himself
    0.88
     subordinates
    0.87
    Activations Density 0.112%

    No Known Activations