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. 2-ATT-KK
    6. 22174
    Prev
    Next
    INDEX
    Explanations

    terms related to global sales and worldwide events or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.05
    2:0.13
    3:0.11
    4:0.06
    5:0.10
    6:0.03
    7:0.04
    8:0.07
    9:0.17
    10:0.08
    11:0.03
    Negative Logits
     analogy
    -1.34
     accus
    -1.20
     rudimentary
    -1.12
     tactic
    -1.11
     wrong
    -1.10
     instincts
    -1.10
     phr
    -1.10
     error
    -1.09
     regression
    -1.08
     inaction
    -1.07
    POSITIVE LOGITS
     神
    1.33
    ゼウス
    1.31
     Jinping
    1.20
    luaj
    1.20
    asia
    1.17
     livest
    1.15
     worldwide
    1.14
    ijing
    1.13
    phia
    1.11
    international
    1.11
    Activations Density 0.016%

    No Known Activations