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. 3-ATT-KK
    6. 8545
    Prev
    Next
    INDEX
    Explanations

    phrases related to humorous or sarcastic commentary involving physical actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.07
    3:0.10
    4:0.02
    5:0.04
    6:0.10
    7:0.28
    8:0.07
    9:0.05
    10:0.06
    11:0.11
    Negative Logits
    ISC
    -1.50
     prepar
    -1.11
    ETF
    -1.11
    venants
    -1.11
     Released
    -1.10
     Instruction
    -1.05
    Catalog
    -1.05
    soDeliveryDate
    -1.05
    ा
    -1.04
     Tradable
    -1.02
    POSITIVE LOGITS
     whining
    1.26
     bitch
    1.24
     ape
    1.10
     mush
    1.10
     biting
    1.07
     fart
    1.07
     stupid
    1.06
     slut
    1.05
     Bender
    1.05
     whine
    1.05
    Activations Density 0.012%

    No Known Activations