© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 28737
    Prev
    Next
    INDEX
    Explanations

    references to studies, surveys, and statistical data regarding social issues

    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
    0:0.05
    1:0.02
    2:0.04
    3:0.09
    4:0.04
    5:0.09
    6:0.02
    7:0.03
    8:0.09
    9:0.13
    10:0.21
    11:0.12
    Negative Logits
    selage
    -1.25
    アル
    -1.22
     arrang
    -1.21
    BuyableInstoreAndOnline
    -1.21
    ascript
    -1.20
     guiIcon
    -1.20
    aintain
    -1.17
    ajo
    -1.17
    ////////////////
    -1.14
    200000
    -1.13
    POSITIVE LOGITS
     OECD
    1.50
     echoes
    1.48
     statistic
    1.41
     Universities
    1.41
     Economist
    1.37
     universities
    1.31
     anecdotal
    1.30
    Studies
    1.29
     epidemic
    1.29
     debunked
    1.24
    Activations Density 0.134%

    No Known Activations