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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 7523
    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 @ 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
    0:0.11
    1:0.16
    2:0.03
    3:0.04
    4:0.03
    5:0.25
    6:0.03
    7:0.03
    8:0.06
    9:0.07
    10:0.07
    11:0.05
    Negative Logits
    版
    -1.79
    assetsadobe
    -1.77
     istg
    -1.62
     photoc
    -1.57
     suspended
    -1.56
     disav
    -1.51
     intermedi
    -1.50
     telev
    -1.49
     wrists
    -1.49
     swast
    -1.46
    POSITIVE LOGITS
    col
    2.03
    hing
    1.89
    ​
    1.89
    ________________
    1.82
    rez
    1.81
    zy
    1.79
    ­
    1.76
    SPONSORED
    1.76
    Dar
    1.75
    ·
    1.74
    Activations Density 0.004%

    No Known Activations