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. 10-ATT-KK
    6. 14713
    Prev
    Next
    INDEX
    Explanations

    references to honor and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.08
    2:0.05
    3:0.05
    4:0.09
    5:0.04
    6:0.09
    7:0.27
    8:0.03
    9:0.05
    10:0.06
    11:0.09
    Negative Logits
     François
    -2.30
    arrell
    -2.13
     Ré
    -2.05
     Trends
    -2.04
    tails
    -2.01
     Dele
    -2.00
     Coleman
    -1.98
     refere
    -1.96
     Tanner
    -1.93
    itaire
    -1.91
    POSITIVE LOGITS
     PB
    2.35
     honor
    2.23
     Xia
    2.21
     ox
    2.17
    ebus
    2.14
     pistol
    2.04
    CDC
    2.01
    ocaust
    2.01
    thia
    2.01
     bee
    1.99
    Activations Density 0.003%

    No Known Activations