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. 8626
    Prev
    Next
    INDEX
    Explanations

    instances of the word "remember."

    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
    0:0.01
    1:0.01
    2:0.09
    3:0.21
    4:0.01
    5:0.03
    6:0.04
    7:0.12
    8:0.13
    9:0.14
    10:0.04
    11:0.11
    Negative Logits
    roy
    -1.15
    monary
    -1.15
    istries
    -1.14
    ikini
    -1.14
    incial
    -1.13
    perse
    -1.13
    qus
    -1.11
    arter
    -1.09
    arters
    -1.07
    matic
    -1.06
    POSITIVE LOGITS
    terday
    1.41
     nostalg
    1.36
     Sheep
    1.21
    ��
    1.18
     recip
    1.18
     Oath
    1.17
     裏�
    1.17
     Scrolls
    1.17
     Zed
    1.15
    acters
    1.14
    Activations Density 0.013%

    No Known Activations