© 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. 9-ATT-KK
    11. 17915
    Prev
    Next
    INDEX
    Explanations

    mentions of financial institutions and their misconduct related to mortgage practices

    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
    0:0.27
    1:0.02
    2:0.18
    3:0.08
    4:0.03
    5:0.08
    6:0.03
    7:0.05
    8:0.09
    9:0.02
    10:0.04
    11:0.03
    Negative Logits
     UNESCO
    -2.73
     Vulkan
    -2.66
     Ern
    -2.60
     Guinness
    -2.43
     Curry
    -2.42
    arij
    -2.39
     Glac
    -2.38
    Tour
    -2.36
    Dur
    -2.35
    stanbul
    -2.33
    POSITIVE LOGITS
     mortgage
    4.56
     Freddie
    4.42
    annie
    4.22
     mortgages
    4.06
     Mortgage
    3.87
     foreclosure
    3.75
     homeowner
    3.65
     homeowners
    3.63
    gage
    3.43
     lenders
    3.29
    Activations Density 0.002%

    No Known Activations