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. 14518
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements in sentences

    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
    0:0.21
    1:0.08
    2:0.09
    3:0.05
    4:0.04
    5:0.04
    6:0.05
    7:0.09
    8:0.03
    9:0.04
    10:0.19
    11:0.06
    Negative Logits
    Palest
    -3.47
     plutonium
    -3.29
     Palest
    -3.10
    yson
    -3.07
     android
    -3.02
    aea
    -2.99
    ryce
    -2.94
    Davis
    -2.85
     Stard
    -2.85
     Russell
    -2.84
    POSITIVE LOGITS
     Hak
    10.43
     Jak
    4.65
     Kak
    4.41
     Hik
    4.33
     Yak
    4.08
     Haku
    3.99
     Zak
    3.96
     Rak
    3.84
     Tak
    3.82
     Hag
    3.75
    Activations Density 0.000%

    No Known Activations