© 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. 8875
    Prev
    Next
    INDEX
    Explanations

    numeric values associated with financial metrics and quantities

    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
    0:0.07
    1:0.02
    2:0.05
    3:0.39
    4:0.02
    5:0.12
    6:0.02
    7:0.04
    8:0.06
    9:0.02
    10:0.11
    11:0.02
    Negative Logits
     Coordinator
    -2.17
     Assass
    -2.09
     moderator
    -1.98
     GROUP
    -1.93
     contention
    -1.93
     coordinator
    -1.92
     staging
    -1.91
     dean
    -1.91
     Director
    -1.89
     QC
    -1.86
    POSITIVE LOGITS
     dollars
    2.73
    coins
    2.53
    pees
    2.43
    etimes
    2.30
    umbs
    2.27
     trillions
    2.22
     billions
    2.22
     euros
    2.20
    abytes
    2.17
     Dollars
    2.17
    Activations Density 0.201%

    No Known Activations