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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 78
    Prev
    Next
    INDEX
    Explanations

    references to software functionality and user experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.01
    2:0.08
    3:0.04
    4:0.06
    5:0.05
    6:0.20
    7:0.04
    8:0.09
    9:0.23
    10:0.02
    11:0.03
    Negative Logits
     Ik
    -4.15
     Hik
    -3.98
     Oilers
    -3.93
    lah
    -3.76
     fitt
    -3.76
    ollah
    -3.70
     herds
    -3.55
     Hawkins
    -3.54
     Nikki
    -3.51
     tatt
    -3.39
    POSITIVE LOGITS
     Chrome
    10.26
     Chromebook
    8.90
    chrome
    8.28
     Chrom
    8.03
     chrome
    7.94
    chrom
    7.15
     chrom
    5.96
     Browser
    5.60
    Browser
    4.93
     Cham
    4.87
    Activations Density 0.006%

    No Known Activations