© 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. 5-ATT-KK
    11. 9490
    Prev
    Next
    INDEX
    Explanations

    terms related to economic or financial challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.04
    3:0.08
    4:0.04
    5:0.03
    6:0.08
    7:0.03
    8:0.16
    9:0.06
    10:0.09
    11:0.25
    Negative Logits
    Stat
    -1.90
     interpol
    -1.86
    Myth
    -1.80
    verages
    -1.71
    BILITIES
    -1.70
     grap
    -1.69
     graphical
    -1.65
     inaccur
    -1.65
     spelled
    -1.64
    attribute
    -1.63
    POSITIVE LOGITS
    etsk
    2.02
    ..........
    2.02
    Building
    1.85
    "),
    1.84
     Delhi
    1.80
    =-=-=-=-=-=-=-=-
    1.79
     Beijing
    1.78
     trench
    1.68
     srfAttach
    1.67
    ")
    1.64
    Activations Density 0.001%

    No Known Activations