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

    Neuronpedia

    Jacobian LensNEW
    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. 9-ATT-KK
    11. 13551
    Prev
    Next
    INDEX
    Explanations

    references to timing and frequency of events

    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
    0:0.03
    1:0.04
    2:0.04
    3:0.06
    4:0.03
    5:0.04
    6:0.01
    7:0.05
    8:0.51
    9:0.02
    10:0.05
    11:0.07
    Negative Logits
     Haitian
    -4.20
     Niagara
    -4.16
     Quebec
    -4.13
     Hartford
    -3.88
     Montreal
    -3.88
     Buffalo
    -3.87
     Dominican
    -3.73
     Winnipeg
    -3.63
     GTA
    -3.56
     Canadiens
    -3.56
    POSITIVE LOGITS
     organising
    4.45
     Corbyn
    4.14
    ilib
    3.93
     recognise
    3.88
     organis
    3.87
     organisation
    3.79
     analys
    3.67
     Ukip
    3.65
     organise
    3.63
     campaigners
    3.62
    Activations Density 0.005%

    No Known Activations