© 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. 9-ATT-KK
    11. 18856
    Prev
    Next
    INDEX
    Explanations

    instances of prepositions and temporal markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.04
    2:0.05
    3:0.05
    4:0.38
    5:0.06
    6:0.04
    7:0.09
    8:0.04
    9:0.05
    10:0.04
    11:0.05
    Negative Logits
     Sevent
    -2.94
     Acid
    -2.59
     NFC
    -2.56
     Indiana
    -2.51
     RG
    -2.36
     Hail
    -2.34
     These
    -2.31
     Twelve
    -2.25
     Enhanced
    -2.25
     Rez
    -2.24
    POSITIVE LOGITS
    EStreamFrame
    2.73
     scrut
    2.66
    comed
    2.60
     mosqu
    2.60
    ounge
    2.57
    pn
    2.52
    ossier
    2.50
    nat
    2.49
    uctor
    2.47
    oeuv
    2.46
    Activations Density 0.038%

    No Known Activations