© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 13190
    Prev
    Next
    INDEX
    Explanations

    terms associated with economic indicators and fluctuations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.16
    2:0.07
    3:0.13
    4:0.11
    5:0.02
    6:0.06
    7:0.17
    8:0.03
    9:0.04
    10:0.05
    11:0.08
    Negative Logits
    Extra
    -2.33
     Remy
    -2.21
    !/
    -2.15
     extras
    -2.10
     amuse
    -2.09
     inter
    -2.05
     Extra
    -1.95
     Exclusive
    -1.94
     Int
    -1.93
    acio
    -1.93
    POSITIVE LOGITS
     declines
    4.20
     decline
    4.07
     declining
    3.29
     deterioration
    3.08
     stagnation
    2.95
     contraction
    2.94
     decrease
    2.80
     stabilization
    2.71
    ware
    2.67
    stead
    2.66
    Activations Density 0.055%

    No Known Activations