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

    Neuronpedia

    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. 9844
    Prev
    Next
    INDEX
    Explanations

    phrases related to corporate announcements and economic growth

    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
    0:0.08
    1:0.02
    2:0.07
    3:0.04
    4:0.06
    5:0.03
    6:0.16
    7:0.03
    8:0.13
    9:0.26
    10:0.02
    11:0.03
    Negative Logits
    jc
    -4.38
     Johnston
    -4.33
     Ethiopian
    -4.17
    jj
    -3.98
    jen
    -3.88
     Ethiop
    -3.85
    Johnson
    -3.80
     Ethiopia
    -3.76
     Huckabee
    -3.75
     Jamaica
    -3.66
    POSITIVE LOGITS
     Aurora
    9.68
     Aur
    8.66
     aur
    8.32
     Aura
    5.15
     Urs
    4.31
     Bore
    4.31
     aura
    4.26
    aur
    4.25
     dement
    4.17
     Aure
    4.14
    Activations Density 0.001%

    No Known Activations