© 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. 10-ATT-KK
    11. 21057
    Prev
    Next
    INDEX
    Explanations

    financial terminology and reference to monetary transactions

    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
    0:0.11
    1:0.13
    2:0.06
    3:0.07
    4:0.03
    5:0.03
    6:0.11
    7:0.11
    8:0.02
    9:0.06
    10:0.17
    11:0.05
    Negative Logits
     Jinn
    -2.82
     Maya
    -2.72
     polygamy
    -2.62
    igham
    -2.57
     Korra
    -2.54
     Coffin
    -2.52
    apache
    -2.52
     Lovecraft
    -2.50
     Avatar
    -2.44
    pox
    -2.40
    POSITIVE LOGITS
     Deutsche
    7.35
    utsche
    6.04
     Der
    3.71
     Frankfurt
    3.61
     Bundes
    3.58
     Bayern
    3.33
     Lever
    3.27
    Der
    3.26
    De
    3.23
     Bank
    3.19
    Activations Density 0.001%

    No Known Activations