© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 10708
    Prev
    Next
    INDEX
    Explanations

    cooking instructions related to the preparation stages of dishes

    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
    1:0.11
    2:0.08
    3:0.03
    4:0.05
    5:0.11
    6:0.06
    7:0.08
    8:0.14
    9:0.12
    10:0.08
    11:0.07
    Negative Logits
    覚醒
    -1.38
    BuyableInstoreAndOnline
    -1.33
     aliases
    -1.32
     Quote
    -1.31
    vertisement
    -1.27
    20439
    -1.26
    ンジ
    -1.26
    機
    -1.22
     Mehran
    -1.22
    YR
    -1.22
    POSITIVE LOGITS
     recess
    1.51
    riger
    1.49
     stabilized
    1.43
     freeze
    1.37
     froze
    1.36
     plateau
    1.28
     refriger
    1.26
     cooled
    1.25
    proof
    1.23
     pregn
    1.21
    Activations Density 0.013%

    No Known Activations