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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10596
    Prev
    Next
    INDEX
    Explanations

    references to political tensions and diplomatic relations involving North Korea and its interactions with other countries

    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
    0:0.04
    1:0.10
    2:0.10
    3:0.05
    4:0.06
    5:0.09
    6:0.10
    7:0.10
    8:0.12
    9:0.06
    10:0.07
    11:0.08
    Negative Logits
    Reviewer
    -1.12
    Finish
    -1.03
    peak
    -1.01
    NetMessage
    -0.95
     🙂
    -0.94
     :)
    -0.94
    lde
    -0.92
     whats
    -0.92
    Untitled
    -0.92
     Pastebin
    -0.90
    POSITIVE LOGITS
    throp
    1.06
    kefeller
    1.01
    者
    0.99
    anwhile
    0.98
    philis
    0.96
    ospons
    0.93
     Romero
    0.89
    orio
    0.88
     Brookings
    0.85
     Rosenthal
    0.85
    Activations Density 0.603%

    No Known Activations