© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 36154
    Prev
    Next
    INDEX
    Explanations

    significant anniversaries and milestones related to historical events and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.10
    3:0.18
    4:0.19
    5:0.03
    6:0.03
    7:0.10
    8:0.06
    9:0.05
    10:0.09
    11:0.08
    Negative Logits
    ubes
    -1.63
    asking
    -1.58
    rack
    -1.58
    initely
    -1.56
     tray
    -1.56
    irds
    -1.53
    eatures
    -1.51
    */(
    -1.50
    bats
    -1.49
    etheless
    -1.43
    POSITIVE LOGITS
     Revolution
    1.75
     Massacre
    1.62
     massacre
    1.61
     Pact
    1.50
     killings
    1.48
     Apocalypse
    1.45
     captivity
    1.44
    killing
    1.42
     apartheid
    1.41
     Deng
    1.41
    Activations Density 0.007%

    No Known Activations