© 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. 12582
    Prev
    Next
    INDEX
    Explanations

    financial metrics and terms related to fiscal policies

    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
    0:0.07
    1:0.11
    2:0.05
    3:0.07
    4:0.02
    5:0.02
    6:0.18
    7:0.25
    8:0.02
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
     clipboard
    -2.40
     ladder
    -2.24
     ambul
    -2.18
    SPA
    -2.18
     importing
    -2.17
     interstate
    -2.09
     Lanc
    -2.09
    ysc
    -2.03
     contribut
    -2.01
    bestos
    -2.01
    POSITIVE LOGITS
     Fiscal
    2.79
     fiscal
    2.75
    iscal
    2.34
    deb
    2.31
    rix
    2.29
    KS
    2.24
     Devils
    2.15
    eki
    2.13
    retty
    2.13
    Sense
    2.11
    Activations Density 0.015%

    No Known Activations