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. 10341
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating locations or settings related to activities and events

    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
    1:0.03
    2:0.21
    3:0.05
    4:0.02
    5:0.02
    6:0.11
    7:0.09
    8:0.16
    9:0.06
    10:0.09
    11:0.07
    Negative Logits
    thia
    -1.27
    ع
    -1.04
     oneself
    -1.01
    hematically
    -1.00
     Saudis
    -0.99
    DERR
    -0.99
     Mourinho
    -0.98
    Muslims
    -0.98
     Muslims
    -0.97
    ł
    -0.97
    POSITIVE LOGITS
     doorstep
    1.47
     headquarters
    1.40
     counterparts
    1.30
     intersection
    1.25
     institution
    1.23
     behest
    1.20
     lair
    1.17
     vantage
    1.15
     entrance
    1.14
     counterpart
    1.14
    Activations Density 0.022%

    No Known Activations