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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 28599
    Prev
    Next
    INDEX
    Explanations

    instances of sourced references or citations in a document

    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
    0:0.17
    1:0.26
    2:0.05
    3:0.04
    4:0.03
    5:0.08
    6:0.06
    7:0.03
    8:0.10
    9:0.05
    10:0.05
    11:0.04
    Negative Logits
     monop
    -1.91
    iage
    -1.74
     conve
    -1.72
     spar
    -1.69
    ixel
    -1.65
    achine
    -1.64
    emis
    -1.62
    aven
    -1.60
     tremend
    -1.60
    perture
    -1.59
    POSITIVE LOGITS
     REUTERS
    2.14
     Medline
    2.05
     EPA
    2.00
     CDC
    2.00
     PubMed
    1.91
     NRL
    1.89
     ISI
    1.88
    APD
    1.86
     Editors
    1.85
     MSM
    1.84
    Activations Density 0.001%

    No Known Activations