© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 8251
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "of" in various contexts

    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
    0:0.03
    1:0.05
    2:0.15
    3:0.16
    4:0.03
    5:0.03
    6:0.14
    7:0.10
    8:0.05
    9:0.10
    10:0.08
    11:0.03
    Negative Logits
    isky
    -1.14
    ̶
    -1.13
     wiret
    -1.06
     Cance
    -1.06
    ertodd
    -1.05
     unexpectedly
    -1.04
    emn
    -1.02
    ═
    -1.01
     irre
    -1.00
     recogn
    -0.99
    POSITIVE LOGITS
     ↑
    1.32
    ��
    1.28
    adian
    1.24
    anas
    1.21
    alon
    1.17
    lite
    1.17
    lord
    1.12
    reading
    1.10
    nostic
    1.10
    unta
    1.10
    Activations Density 0.012%

    No Known Activations