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. 14734
    Prev
    Next
    INDEX
    Explanations

    references to the planet or environment

    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
    0:0.06
    1:0.08
    2:0.09
    3:0.09
    4:0.09
    5:0.08
    6:0.07
    7:0.08
    8:0.06
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
     BYU
    -2.63
    thodox
    -2.51
     CLSID
    -2.43
    Override
    -2.42
    arsity
    -2.38
     Hebrew
    -2.37
     ⓘ
    -2.35
    SHA
    -2.34
    Catalog
    -2.33
    ּ
    -2.33
    POSITIVE LOGITS
     mosquito
    2.64
     nas
    2.51
     Flor
    2.50
     Armen
    2.47
     Vie
    2.46
     Cors
    2.40
    Balt
    2.38
     Axel
    2.37
     Darling
    2.34
     Nas
    2.29
    Activations Density 0.000%

    No Known Activations