© 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. 28541
    Prev
    Next
    INDEX
    Explanations

    phrases related to timelines and progress in projects or events

    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
    0:0.07
    1:0.03
    2:0.08
    3:0.30
    4:0.05
    5:0.05
    6:0.02
    7:0.03
    8:0.04
    9:0.10
    10:0.10
    11:0.09
    Negative Logits
     temperament
    -1.56
    entimes
    -1.55
     aest
    -1.52
    xual
    -1.52
     relational
    -1.44
     ancest
    -1.43
    luaj
    -1.42
    SourceFile
    -1.40
     ail
    -1.40
    endif
    -1.39
    POSITIVE LOGITS
     OFFIC
    1.97
     ANN
    1.81
     FIN
    1.74
     announces
    1.57
    icial
    1.57
     INC
    1.56
     Begins
    1.49
     Authorities
    1.49
     Updated
    1.47
     LIVE
    1.46
    Activations Density 0.173%

    No Known Activations