© 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. 43723
    Prev
    Next
    INDEX
    Explanations

    mentions of specific years and the context surrounding historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.06
    1:0.06
    2:0.04
    3:0.04
    4:0.03
    5:0.31
    6:0.03
    7:0.02
    8:0.05
    9:0.10
    10:0.11
    11:0.09
    Negative Logits
    emis
    -1.48
    ahi
    -1.46
    fish
    -1.44
    apons
    -1.42
    ava
    -1.37
    atin
    -1.36
    onis
    -1.32
     Tycoon
    -1.32
    killer
    -1.30
    ola
    -1.28
    POSITIVE LOGITS
     onwards
    1.75
     timeframe
    1.62
     onward
    1.46
    Attempt
    1.29
     Ago
    1.22
    ruary
    1.16
     Composite
    1.15
     Era
    1.14
     Coh
    1.14
    terms
    1.14
    Activations Density 0.193%

    No Known Activations