© 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. 3132
    Prev
    Next
    INDEX
    Explanations

    significant dates and events in a narrative context

    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
    0:0.01
    1:0.01
    2:0.20
    3:0.16
    4:0.08
    5:0.03
    6:0.02
    7:0.04
    8:0.09
    9:0.07
    10:0.12
    11:0.10
    Negative Logits
    harm
    -1.43
     prevail
    -1.36
    resist
    -1.32
    abus
    -1.27
    ratom
    -1.27
    "},{"
    -1.27
    pport
    -1.27
     scatter
    -1.25
    "/>
    -1.24
    uum
    -1.24
    POSITIVE LOGITS
     Lyon
    1.47
     Jan
    1.46
     Ced
    1.46
     Sept
    1.46
     Buenos
    1.43
     Jerome
    1.39
     Lia
    1.37
     Jos
    1.35
     Zub
    1.34
     Yak
    1.34
    Activations Density 0.640%

    No Known Activations