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. 1-ATT-KK
    6. 6366
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions, contracts, and legal agreements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.22
    1:0.12
    2:0.06
    3:0.03
    4:0.07
    5:0.11
    6:0.06
    7:0.06
    8:0.02
    9:0.02
    10:0.05
    11:0.12
    Negative Logits
     skins
    -1.33
    iour
    -1.30
    ologies
    -1.29
    onto
    -1.29
    fax
    -1.27
     improves
    -1.26
     vitamins
    -1.26
    cation
    -1.25
    lands
    -1.25
    ilies
    -1.23
    POSITIVE LOGITS
    CLASSIFIED
    1.62
     Stage
    1.48
     psychiat
    1.48
     Arkham
    1.47
     KGB
    1.44
     サーティワン
    1.41
    EStream
    1.41
     happiest
    1.41
     Geh
    1.38
     Borough
    1.33
    Activations Density 0.584%

    No Known Activations