Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7771
    Prev
    Next
    INDEX
    Explanations

    phrases indicating immediacy or current relevance

    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
    1:0.03
    2:0.11
    3:0.03
    4:0.02
    5:0.04
    6:0.15
    7:0.23
    8:0.05
    9:0.08
    10:0.07
    11:0.14
    Negative Logits
     breakup
    -1.11
     mask
    -1.06
    hid
    -1.06
    formance
    -0.97
     acronym
    -0.96
    urat
    -0.95
     triangle
    -0.94
    ミ
    -0.93
    arb
    -0.93
    duty
    -0.91
    POSITIVE LOGITS
    seekers
    1.06
    zyk
    1.01
    OIL
    1.00
    wat
    0.96
    SPONSORED
    0.94
     sear
    0.90
     archaeologists
    0.90
    sql
    0.90
     Wik
    0.90
    emis
    0.89
    Activations Density 0.017%

    No Known Activations